@inproceedings{Moore2021,
	title = {Processing pipelines for efficient, physically-accurate simulation of microphone array signals in dynamic sound scenes},
	doi = {10.1109/ICASSP39728.2021.9413354},
	abstract = {Multichannel acoustic signal processing is predicated on the fact that the interchannel relationships between the received signals can be exploited to infer information about the acoustic scene. Recently there has been increasing interest in algorithms which are applicable in dynamic scenes, where the source(s) and/or microphone array may be moving. Simulating such scenes has particular challenges which are exacerbated when real-time, listener-in-the-loop evaluation of algorithms is required. This paper considers candidate pipelines for simulating the array response to a set of point/image sources in terms of their accuracy, scalability and continuity. A new approach, in which the filter kernels are obtained using principal component analysis from time-aligned impulse responses, is proposed. When the number of filter kernels is ≤40 the new approach achieves more accurate simulation than competing methods.},
	booktitle = {{ICASSP}},
	author = {Moore, Alastair H. and Vos, Rebecca R. and Naylor, Patrick A. and Brookes, Mike},
	month = jun,
	year = {2021},
	note = {ISSN: 2379-190X},
	keywords = {Acoustic arrays, Array signal processing, Heuristic algorithms, Microphone arrays, Pipelines, Scalability, Signal processing algorithms, acoustic simulation, head movement, hearing aids, microphone arrays, virtual reality},
	pages = {965--969},
}

Multichannel acoustic signal processing is predicated on the fact that the interchannel relationships between the received signals can be exploited to infer information about the acoustic scene. Recently there has been increasing interest in algorithms which are applicable in dynamic scenes, where the source(s) and/or microphone array may be moving. Simulating such scenes has particular challenges which are exacerbated when real-time, listener-in-the-loop evaluation of algorithms is required. This paper considers candidate pipelines for simulating the array response to a set of point/image sources in terms of their accuracy, scalability and continuity. A new approach, in which the filter kernels are obtained using principal component analysis from time-aligned impulse responses, is proposed. When the number of filter kernels is ≤40 the new approach achieves more accurate simulation than competing methods.

@article{Moore2019,
	title = {Noise covariance matrix estimation for rotating microphone arrays},
	volume = {27},
	issn = {2329-9290},
	doi = {10.1109/TASLP.2018.2882307},
	abstract = {The noise covariance matrix computed between the signals from a microphone array is used in the design of spatial filters and beamformers with applications in noise suppression and dereverberation. This paper specifically addresses the problem of estimating the covariance matrix associated with a noise field when the array is rotating during desired source activity, as is common in head-mounted arrays. We propose a parametric model that leads to an analytical expression for the microphone signal covariance as a function of the array orientation and array manifold. An algorithm for estimating the model parameters during noise-only segments is proposed and the performance shown to be improved, rather than degraded, by array rotation. The stored model parameters can then be used to update the covariance matrix to account for the effects of any array rotation that occurs when the desired source is active. The proposed method is evaluated in terms of the Frobenius norm of the error in the estimated covariance matrix and of the noise reduction performance of a minimum variance distortionless response beamformer. In simulation experiments the proposed method achieves 18 dB lower error in the estimated noise covariance matrix than a conventional recursive averaging approach and results in noise reduction which is within 0.05 dB of an oracle beamformer using the ground truth noise covariance matrix.},
	number = {3},
	journal = {IEEE\_ACM\_J\_ASLP},
	author = {Moore, A. H. and Xue, W. and Naylor, P. A. and Brookes, M.},
	month = mar,
	year = {2019},
	pages = {519--530},
}

The noise covariance matrix computed between the signals from a microphone array is used in the design of spatial filters and beamformers with applications in noise suppression and dereverberation. This paper specifically addresses the problem of estimating the covariance matrix associated with a noise field when the array is rotating during desired source activity, as is common in head-mounted arrays. We propose a parametric model that leads to an analytical expression for the microphone signal covariance as a function of the array orientation and array manifold. An algorithm for estimating the model parameters during noise-only segments is proposed and the performance shown to be improved, rather than degraded, by array rotation. The stored model parameters can then be used to update the covariance matrix to account for the effects of any array rotation that occurs when the desired source is active. The proposed method is evaluated in terms of the Frobenius norm of the error in the estimated covariance matrix and of the noise reduction performance of a minimum variance distortionless response beamformer. In simulation experiments the proposed method achieves 18 dB lower error in the estimated noise covariance matrix than a conventional recursive averaging approach and results in noise reduction which is within 0.05 dB of an oracle beamformer using the ground truth noise covariance matrix.

@inproceedings{Moore2018,
	address = {Calgery, Canada},
	title = {Room identification using frequency dependence of spectral decay statistics},
	abstract = {A method for room identification is proposed based on the reverber- ation properties of multichannel speech recordings. The approach exploits the dependence of spectral decay statistics on the reverber- ation time of a room. The average negative-side variance within 1/3- octave bands is proposed as the identifying feature and shown to be effective in a classification experiment. However, negative-side vari- ance is also dependent on the direct-to-reverberant energy ratio. The resulting sensitivity to different spatial configurations of source and microphones within a room are mitigated using a novel reverberation enhancement algorithm. A classification experiment using speech convolved with measured impulse responses and contaminated with environmental noise demonstrates the effectiveness of the proposed method, achieving 79\% correct identification in the most demanding condition compared to 40\% using unenhanced signals.},
	booktitle = {{ICASSP}},
	author = {Moore, Alastair H. and Naylor, Patrick A. and Brookes, Mike},
	month = apr,
	year = {2018},
}

A method for room identification is proposed based on the reverber- ation properties of multichannel speech recordings. The approach exploits the dependence of spectral decay statistics on the reverber- ation time of a room. The average negative-side variance within 1/3- octave bands is proposed as the identifying feature and shown to be effective in a classification experiment. However, negative-side vari- ance is also dependent on the direct-to-reverberant energy ratio. The resulting sensitivity to different spatial configurations of source and microphones within a room are mitigated using a novel reverberation enhancement algorithm. A classification experiment using speech convolved with measured impulse responses and contaminated with environmental noise demonstrates the effectiveness of the proposed method, achieving 79% correct identification in the most demanding condition compared to 40% using unenhanced signals.

@article{Xue2018a,
	title = {Modulation-{Domain} {Multichannel} {Kalman} {Filtering} for {Speech} {Enhancement}},
	volume = {26},
	issn = {2329-9290},
	doi = {10.1109/TASLP.2018.2845665},
	abstract = {Compared with single-channel speech enhancement methods, multichannel methods can utilize spatial information to design optimal filters. Although some filters adaptively consider second-order signal statistics, the temporal evolution of the speech spectrum is usually neglected. By using linear prediction (LP) to model the inter-frame temporal evolution of speech, single-channel Kalman filtering (KF) based methods have been developed for speech enhancement. In this paper, we derive a multichannel KF (MKF) that jointly uses both interchannel spatial correlation and interframe temporal correlation for speech enhancement. We perform LP in the modulation domain, and by incorporating the spatial information, derive an optimal MKF gain in the short-time Fourier transform domain. We show that the proposed MKF reduces to the conventional multichannel Wiener filter if the LP information is discarded. Furthermore, we show that, under an appropriate assumption, the MKF is equivalent to a concatenation of the minimum variance distortion response beamformer and a single-channel modulation-domain KF and therefore present an alternative implementation of the MKF. Experiments conducted on a public head-related impulse response database demonstrate the effectiveness of the proposed method.},
	number = {10},
	journal = {IEEE\_ACM\_J\_ASLP},
	author = {Xue, W. and Moore, A. H. and Brookes, M. and Naylor, P. A.},
	month = oct,
	year = {2018},
	pages = {1833--1847},
}

Compared with single-channel speech enhancement methods, multichannel methods can utilize spatial information to design optimal filters. Although some filters adaptively consider second-order signal statistics, the temporal evolution of the speech spectrum is usually neglected. By using linear prediction (LP) to model the inter-frame temporal evolution of speech, single-channel Kalman filtering (KF) based methods have been developed for speech enhancement. In this paper, we derive a multichannel KF (MKF) that jointly uses both interchannel spatial correlation and interframe temporal correlation for speech enhancement. We perform LP in the modulation domain, and by incorporating the spatial information, derive an optimal MKF gain in the short-time Fourier transform domain. We show that the proposed MKF reduces to the conventional multichannel Wiener filter if the LP information is discarded. Furthermore, we show that, under an appropriate assumption, the MKF is equivalent to a concatenation of the minimum variance distortion response beamformer and a single-channel modulation-domain KF and therefore present an alternative implementation of the MKF. Experiments conducted on a public head-related impulse response database demonstrate the effectiveness of the proposed method.

@inproceedings{Xue2018,
	title = {Multichannel {Kalman} filtering for speech ehnancement},
	doi = {10.1109/ICASSP.2018.8461903},
	abstract = {The use of spatial information in multichannel speech enhancement methods is well established but information associated with the temporal evolution of speech is less commonly exploited. Speech signals can be modelled using an autoregressive process in the time-frequency modulation domain, and Kalman filtering based speech enhancement algorithms have been developed for single-channel processing. In this paper, a multichannel Kalman filter (MKF) for speech enhancement is derived that jointly considers the multichannel spatial information and the temporal correlations of speech. We model the temporal evolution of speech in the modulation domain and, by incorporating the spatial information, an optimal MKF gain is derived in the short-time Fourier transform domain. We also show that the proposed MKF becomes a conventional multichannel Wiener filter if the temporal information is discarded. Experiments using the signals generated from a public head-related impulse response database demonstrate the effectiveness of the proposed method in comparison to other techniques.},
	booktitle = {{ICASSP}},
	author = {Xue, W. and Moore, A. H. and Brookes, M. and Naylor, P. A.},
	month = apr,
	year = {2018},
	pages = {41--45},
}

The use of spatial information in multichannel speech enhancement methods is well established but information associated with the temporal evolution of speech is less commonly exploited. Speech signals can be modelled using an autoregressive process in the time-frequency modulation domain, and Kalman filtering based speech enhancement algorithms have been developed for single-channel processing. In this paper, a multichannel Kalman filter (MKF) for speech enhancement is derived that jointly considers the multichannel spatial information and the temporal correlations of speech. We model the temporal evolution of speech in the modulation domain and, by incorporating the spatial information, an optimal MKF gain is derived in the short-time Fourier transform domain. We also show that the proposed MKF becomes a conventional multichannel Wiener filter if the temporal information is discarded. Experiments using the signals generated from a public head-related impulse response database demonstrate the effectiveness of the proposed method in comparison to other techniques.

@inproceedings{Moore2018a,
	address = {Tokyo, Japan},
	title = {Binaural mask-informed speech enhancement for hearing aids with head tracking},
	booktitle = {{IWAENC}},
	author = {Moore, Alastair H. and Lightburn, Leo and Xue, Wei and Naylor, Patrick A and Brookes, Mike},
	month = sep,
	year = {2018},
}

@inproceedings{Moore2017,
	title = {Robust spherical harmonic domain interpolation of spatially sampled array manifolds},
	doi = {10.1109/ICASSP.2017.7952210},
	booktitle = {{ICASSP}},
	author = {Moore, Alastair H. and Brookes, Mike and Naylor, Patrick A.},
	year = {2017},
}

@inproceedings{Lollmann2017,
	title = {Microphone array signal processing for robot audition},
	doi = {10.1109/HSCMA.2017.7895560},
	abstract = {Robot audition for humanoid robots interacting naturally with humans in an unconstrained real-world environment is a hitherto unsolved challenge. The recorded microphone signals are usually distorted by background and interfering noise sources (speakers) as well as room reverberation. In addition, the movements of a robot and its actuators cause ego-noise which degrades the recorded signals significantly. The movement of the robot body and its head also complicates the detection and tracking of the desired, possibly moving, sound sources of interest. This paper presents an overview of the concepts in microphone array processing for robot audition and some recent achievements.},
	booktitle = {{HSCMA}},
	author = {Löllmann, H. W. and Moore, A. H. and Naylor, P. A. and Rafaely, B. and Horaud, R. and Mazel, A. and Kellermann, W.},
	month = mar,
	year = {2017},
	pages = {51--55},
}

Robot audition for humanoid robots interacting naturally with humans in an unconstrained real-world environment is a hitherto unsolved challenge. The recorded microphone signals are usually distorted by background and interfering noise sources (speakers) as well as room reverberation. In addition, the movements of a robot and its actuators cause ego-noise which degrades the recorded signals significantly. The movement of the robot body and its head also complicates the detection and tracking of the desired, possibly moving, sound sources of interest. This paper presents an overview of the concepts in microphone array processing for robot audition and some recent achievements.

@inproceedings{Hafezi2017a,
	title = {Multi-source estimation consistency for improved multiple direction-of-arrival estimation},
	doi = {10.1109/HSCMA.2017.7895566},
	booktitle = {{HSCMA}},
	author = {Hafezi, Sina and Moore, Alastair H. and Naylor, Patrick A.},
	year = {2017},
}

@article{Hafezi2017b,
	title = {Augmented intensity vectors for direction of arrival estimation in the spherical harmonic domain},
	volume = {25},
	issn = {2329-9290},
	doi = {10.1109/TASLP.2017.2736067},
	abstract = {Pseudointensity vectors (PIVs) provide a means of direction of arrival (DOA) estimation for spherical microphone arrays using only the zeroth and the first-order spherical harmonics. An augmented intensity vector (AIV) is proposed which improves the accuracy of PIVs by exploiting higher order spherical harmonics. We compared DOA estimation using our proposed AIVs against PIVs, steered response power (SRP) and subspace methods where the number of sources, their angular separation, the reverberation time of the room and the sensor noise level are varied. The results show that the proposed approach outperforms the baseline methods and performs at least as accurately as the state-of-theart method with strong robustness to reverberation, sensor noise, and number of sources. In the single and multiple source scenarios tested, which include realistic levels of reverberation and noise, the proposed method had average error of 1.5° and 2°, respectively.},
	number = {10},
	journal = {IEEE\_ACM\_J\_ASLP},
	author = {Hafezi, S. and Moore, A. H. and Naylor, P. A.},
	month = oct,
	year = {2017},
	pages = {1956--1968},
}

Pseudointensity vectors (PIVs) provide a means of direction of arrival (DOA) estimation for spherical microphone arrays using only the zeroth and the first-order spherical harmonics. An augmented intensity vector (AIV) is proposed which improves the accuracy of PIVs by exploiting higher order spherical harmonics. We compared DOA estimation using our proposed AIVs against PIVs, steered response power (SRP) and subspace methods where the number of sources, their angular separation, the reverberation time of the room and the sensor noise level are varied. The results show that the proposed approach outperforms the baseline methods and performs at least as accurately as the state-of-theart method with strong robustness to reverberation, sensor noise, and number of sources. In the single and multiple source scenarios tested, which include realistic levels of reverberation and noise, the proposed method had average error of 1.5° and 2°, respectively.

@inproceedings{Hafezi2017,
	title = {Multiple source localization using estimation consistency in the time-frequency domain},
	doi = {10.1109/ICASSP.2017.7952209},
	booktitle = {{ICASSP}},
	author = {Hafezi, Sina and Moore, Alastair H. and Naylor, Patrick A.},
	year = {2017},
}

@patent{Eaton2017b,
	title = {Reverberation estimator},
	shorttitle = {United {States} {Patent}},
	url = {http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=9799322.PN.},
	abstract = {Provided are methods and systems for generating Direct-to-Reverberant
     Ratio (DRR) estimates. The methods and systems use a null-steered
     beamformer to produce accurate DRR estimates across a variety of room
     sizes, reverberation times, and source-receiver distances. The DRR
     estimation algorithm uses spatial selectivity to separate direct and
     reverberant energy and account for noise separately. The formulation
     considers the response of the beamformer to reverberant sound and the
     effect of noise. The DRR estimation algorithm is more robust to
     background noise than existing approaches, and is applicable where a
     signal is recorded with two or more microphones, such as with mobile
     communications devices, laptop computers, and the like.},
	assignee = {Google Inc.},
	number = {9799322},
	urldate = {2017-10-30},
	author = {Eaton, D. James and Moore, Alastair H. and Naylor, Patrick A. and Skoglund, Jan},
	month = oct,
	year = {2017},
}

Provided are methods and systems for generating Direct-to-Reverberant Ratio (DRR) estimates. The methods and systems use a null-steered beamformer to produce accurate DRR estimates across a variety of room sizes, reverberation times, and source-receiver distances. The DRR estimation algorithm uses spatial selectivity to separate direct and reverberant energy and account for noise separately. The formulation considers the response of the beamformer to reverberant sound and the effect of noise. The DRR estimation algorithm is more robust to background noise than existing approaches, and is applicable where a signal is recorded with two or more microphones, such as with mobile communications devices, laptop computers, and the like.

@inproceedings{Yiallourides2017,
	title = {A dynamic programming approach for automatic stride detection and segmentation in acoustic emission from the knee},
	doi = {10.1109/ICASSP.2017.7952186},
	booktitle = {{ICASSP}},
	author = {Yiallourides, Costas and Manning-Eid, Victoria and Moore, Alastair H. and Naylor, Patrick A.},
	year = {2017},
}

@inproceedings{Lightburn2017,
	title = {Improving the perceptual quality of ideal binary masked speech},
	doi = {10.1109/ICASSP.2017.7952238},
	booktitle = {{ICASSP}},
	author = {Lightburn, Leo and De Sena, Enzo and Moore, Alastair H. and Naylor, Patrick A. and Brookes, Mike},
	month = mar,
	year = {2017},
}

@article{Moore2016b,
	title = {Direction of arrival estimation in the spherical harmonic domain using subspace psuedointensity vectors},
	volume = {25},
	doi = {10.1109/TASLP.2016.2613280},
	number = {1},
	journal = {IEEE\_ACM\_J\_ASLP},
	author = {Moore, Alastair H. and Evers, Christine and Naylor, Patrick A.},
	month = jan,
	year = {2017},
	note = {tex.owner= amoore1},
	pages = {178--192},
}

@article{Moore2016c,
	title = {Speech enhancement for robust automatic speech recognition: {Evaluation} using a baseline system and instrumental measures},
	volume = {46},
	doi = {10.1016/j.csl.2016.11.003},
	journal = {J\_CSL},
	author = {Moore, Alastair H. and Parada, Pablo Peso and Naylor, Patrick A.},
	month = nov,
	year = {2017},
	note = {tex.owner= amoore1},
	pages = {574--584},
}

@inproceedings{Moore2016a,
	title = {Linear prediction based dereverberation for spherical microphone arrays},
	doi = {10.1109/IWAENC.2016.7602946},
	booktitle = {{IWAENC}},
	author = {Moore, Alastair H. and Naylor, Patrick A.},
	year = {2016},
	note = {tex.owner= amoore1},
}

@inproceedings{Moore2016,
	title = {{2D} direction of arrival estimation of multiple moving sources using a spherical microphone array},
	doi = {10.1109/EUSIPCO.2016.7760442},
	booktitle = {{EUSIPCO}},
	author = {Moore, Alastair H. and Evers, Christine and Naylor, Patrick A.},
	year = {2016},
	note = {tex.owner= amoore1},
}

@inproceedings{Javed2016a,
	title = {Spherical harmonic rake receivers for dereverberation},
	doi = {10.1109/IWAENC.2016.7602944},
	booktitle = {{IWAENC}},
	author = {Javed, Hamza A. and Moore, Alastair H. and Naylor, Patrick A.},
	year = {2016},
	note = {tex.owner= amoore1},
}

@inproceedings{Javed2016,
	address = {Shanghai, China},
	title = {Spherical microphone array acoustic rake receivers},
	doi = {10.1109/ICASSP.2016.7471647},
	booktitle = {{ICASSP}},
	author = {Javed, H. A. and Moore, A. H. and Naylor, P. A.},
	month = mar,
	year = {2016},
	note = {tex.owner= wxue},
}

@inproceedings{Hafezi2016a,
	title = {Multiple source localization in the spherical harmonic domain using augmented intensity vectors based on grid search},
	booktitle = {{EUSIPCO}},
	author = {Hafezi, Sina and Moore, Alastair H. and Naylor, Patrick A.},
	year = {2016},
	note = {tex.owner= amoore1},
}

@inproceedings{Hafezi2016,
	title = {{3D} acoustic source localization in the spherical harmonic domain based on optimized grid search},
	booktitle = {{ICASSP}},
	author = {Hafezi, Sina and Moore, Alastair H. and Naylor, Patrick A.},
	year = {2016},
	note = {tex.owner= amoore1},
}

@inproceedings{Evers2016c,
	address = {Budapest, Hungary},
	title = {Localization of moving microphone arrays from moving sound sources for robot audition},
	booktitle = {{EUSIPCO}},
	author = {Evers, C. and Moore, A. H. and Naylor, P. A.},
	year = {2016},
	note = {tex.owner= cevers},
}

@inproceedings{Evers2016a,
	address = {Aachen, Germany},
	title = {Towards informative path planning for acoustic simultaneous localization of microphone arrays and mapping of surrounding sound sources (a-{SLAM})},
	booktitle = {{DAGA}},
	author = {Evers, C. and Moore, A. H. and Naylor, P. A.},
	month = mar,
	year = {2016},
	note = {tex.owner= cevers},
}

@inproceedings{Evers2016,
	address = {Shanghai, China},
	title = {Acoustic simultaneous localization and mapping (a-{SLAM}) of a moving microphone array and its surrounding speakers},
	doi = {10.1109/ICASSP.2016.7471626},
	booktitle = {{ICASSP}},
	author = {Evers, C. and Moore, A. H. and Naylor, P. A.},
	month = mar,
	year = {2016},
	note = {tex.owner= cevers},
}

@techreport{Eaton2015e,
	type = {Technical {Report}},
	title = {{ACE} challenge results technical report},
	url = {https://arxiv.org/abs/1606.03365},
	institution = {Imperial College London},
	author = {Eaton, James and Gaubitch, Nikolay D. and Moore, Alastair H. and Naylor, Patrick A.},
	year = {2016},
	note = {tex.owner= dje11},
}

@article{Eaton2016,
	title = {Estimation of room acoustic parameters: the {ACE} challenge},
	volume = {24},
	issn = {2329-9290},
	doi = {10.1109/TASLP.2016.2577502},
	abstract = {Reverberation Time (T$_{\textrm{t}}$extrm60) and Direct-to-Reverberant Ratio (DRR) are important parameters which together can characterize sound captured by microphones in non-anechoic rooms. These parameters are important in speech processing applications such as speech recognition and dereverberation. The values of T$_{\textrm{t}}$extrm60 and DRR can be estimated directly from the Acoustic Impulse Response (AIR) of the room. In practice, the AIR is not normally available, in which case these parameters must be estimated blindly from the observed speech in the microphone signal. The Acoustic Characterization of Environments (ACE) Challenge set out to determine the state-of-the-art in blind acoustic parameter estimation and also to stimulate research in this area. A summary of the ACE Challenge, and the corpus used in the challenge is presented together with an analysis of the results. Existing algorithms were submitted alongside novel contributions, the comparative results for which are presented in this paper. The challenge showed that T$_{\textrm{t}}$extrm60 estimation is a mature field where analytical approaches dominate whilst DRR estimation is a less mature field where machine learning approaches are currently more successful.},
	number = {10},
	journal = {IEEE\_ACM\_J\_ASLP},
	author = {Eaton, James and Gaubitch, Nikolay D. and Moore, Alastair H. and Naylor, Patrick A.},
	month = oct,
	year = {2016},
	note = {tex.owner= dje11},
	pages = {1681--1693},
}

Reverberation Time (T$_{\textrm{t}}$extrm60) and Direct-to-Reverberant Ratio (DRR) are important parameters which together can characterize sound captured by microphones in non-anechoic rooms. These parameters are important in speech processing applications such as speech recognition and dereverberation. The values of T$_{\textrm{t}}$extrm60 and DRR can be estimated directly from the Acoustic Impulse Response (AIR) of the room. In practice, the AIR is not normally available, in which case these parameters must be estimated blindly from the observed speech in the microphone signal. The Acoustic Characterization of Environments (ACE) Challenge set out to determine the state-of-the-art in blind acoustic parameter estimation and also to stimulate research in this area. A summary of the ACE Challenge, and the corpus used in the challenge is presented together with an analysis of the results. Existing algorithms were submitted alongside novel contributions, the comparative results for which are presented in this paper. The challenge showed that T$_{\textrm{t}}$extrm60 estimation is a mature field where analytical approaches dominate whilst DRR estimation is a less mature field where machine learning approaches are currently more successful.

@inproceedings{Moore2015,
	address = {Singapore},
	title = {Multichannel equalisation for high-order spherical microphone arrays using beamformed channels},
	booktitle = {{IEEE}\_DSP},
	author = {Moore, Alastair H. and Evers, Christine and Naylor, Patrick A.},
	month = jul,
	year = {2015},
	note = {tex.owner= amoore1},
}

@inproceedings{Moore2015a,
	title = {Direction of arrival estimation using pseudo-intensity vectors with direct-path dominance test},
	booktitle = {{EUSIPCO}},
	author = {Moore, Alastair H. and Evers, Christine and Naylor, P. A. and Alon, David L. and Rafaely, Boaz},
	year = {2015},
	note = {tex.owner= amoore1},
}

@inproceedings{Hafezi2015,
	address = {Nice, France},
	title = {Modelling source directivity in room impulse response simulation for spherical microphone arrays},
	booktitle = {{EUSIPCO}},
	author = {Hafezi, S. and Moore, A. H. and Naylor, P. A.},
	month = sep,
	year = {2015},
	note = {tex.owner= sinahafezi},
}

@inproceedings{Evers2015,
	address = {Singapore},
	title = {Bearing-only acoustic tracking of moving speakers for robot audition},
	booktitle = {{IEEE}\_DSP},
	author = {Evers, Christine and Sheaffer, Jonathan and Moore, Alastair H. and Rafaely, Boaz and Naylor, Patrick A.},
	month = jul,
	year = {2015},
	note = {tex.owner= cevers},
}

@inproceedings{Eaton2015a,
	address = {New Paltz, NY, USA},
	title = {The {ACE} {Challenge} - corpus description and performance evaluation},
	doi = {10.1109/WASPAA.2015.7336912},
	abstract = {Knowledge of the Direct-to-Reverberant Ratio (DRR) and Reverberation Time (T60) can be used to better perform speech and audio processing such as dereverberation. Established methods compute these parameters from measured Acoustic Impulse Responses (AIRs). However, in many practical situations the AIR is not available and the parameters must be estimated non-intrusively directly from noisy speech or audio signals. The Acoustic Characterization of Environments (ACE) Challenge is a competition to identify the most promising non-intrusive DRR and T60 estimation methods using real noisy reverberant speech. We describe the ACE corpus comprising multi-channel AIRs, and multi-channel noise including ambient, fan and babble noise recorded in the same environment as the measured AIRs, along with the corresponding DRR and T60 measurements. The evaluation methodology is discussed and comparative results are shown.},
	booktitle = {{WASPAA}},
	author = {Eaton, J. and Gaubitch, N. D. and Moore, A. H. and Naylor, P. A.},
	year = {2015},
	note = {tex.day= 18-21
tex.owner= dje11},
	keywords = {Acoustics, Arrays, Buildings, Frequency measurement, Microphones, Noise measurement, Speech, acoustic impulse response, speech dereverberation, speech enhancement},
}

Knowledge of the Direct-to-Reverberant Ratio (DRR) and Reverberation Time (T60) can be used to better perform speech and audio processing such as dereverberation. Established methods compute these parameters from measured Acoustic Impulse Responses (AIRs). However, in many practical situations the AIR is not available and the parameters must be estimated non-intrusively directly from noisy speech or audio signals. The Acoustic Characterization of Environments (ACE) Challenge is a competition to identify the most promising non-intrusive DRR and T60 estimation methods using real noisy reverberant speech. We describe the ACE corpus comprising multi-channel AIRs, and multi-channel noise including ambient, fan and babble noise recorded in the same environment as the measured AIRs, along with the corresponding DRR and T60 measurements. The evaluation methodology is discussed and comparative results are shown.

@inproceedings{Eaton2015,
	address = {Brisbane, Australia},
	title = {Direct-to-reverberant ratio estimation using a null-steered beamformer},
	doi = {10.1109/ICASSP.2015.7177929},
	abstract = {Reverberation affects the quality and intelligibility of distant speech recorded in a room. Direct-to-Reverberant Ratio (DRR) is a useful measure for assessing the acoustic configuration and can be used to inform dereverberation algorithms. We describe a novel DRR estimation algorithm applicable where the signal was recorded with two or more microphones, such as mobile communications devices and laptops. The method uses a null-steered beamformer. In simulations the proposed method yields accurate DRR estimates to within +/- 4 dB across a across a wide variety of room sizes, reverberation times and source-receiver distances. It is also shown that the proposed method is more robust to background noise than a baseline approach. The best estimation accuracy is obtained in the region from -5 to 5 dB which is a relevant range for portable devices.},
	booktitle = {{ICASSP}},
	author = {Eaton, James and Moore, Alastair H. and Naylor, Patrick A. and Skoglund, J.},
	month = apr,
	year = {2015},
	note = {tex.owner= dje11},
	keywords = {beamforming, speech dereverberation, speech enhancement},
	pages = {46--50},
}

Reverberation affects the quality and intelligibility of distant speech recorded in a room. Direct-to-Reverberant Ratio (DRR) is a useful measure for assessing the acoustic configuration and can be used to inform dereverberation algorithms. We describe a novel DRR estimation algorithm applicable where the signal was recorded with two or more microphones, such as mobile communications devices and laptops. The method uses a null-steered beamformer. In simulations the proposed method yields accurate DRR estimates to within +/- 4 dB across a across a wide variety of room sizes, reverberation times and source-receiver distances. It is also shown that the proposed method is more robust to background noise than a baseline approach. The best estimation accuracy is obtained in the region from -5 to 5 dB which is a relevant range for portable devices.

@inproceedings{Moore2014a,
	address = {Lisbon, Portugal},
	title = {An analysis of the effect of larynx-synchronous averaging on dereverberation of voiced speech},
	abstract = {The SMERSH algorithm is a physiologically-motivated approach to low-complexity speech dereverberation. It employs multichannel linear prediction to obtain a reverberant residual signal and subsequent larynx-synchronous temporal averaging to attenuate the reverberation during voiced speech. Experimental results suggest the method is successful but, to date, no detailed analysis of the theoretical basis of the larynx-synchronous averaging has been undertaken. In this paper the SMERSH algorithm is reviewed before focussing on the theoretical basis of its approach. We show that the amount of dereverberation that can be achieved depends on the coherence of reverberation between frames. Simulations show that the extent of dereverberation increases with reverberation time and give an insight into the tradeoff between dereverberation and speech distortion.},
	booktitle = {{EUSIPCO}},
	author = {Moore, A. H. and Naylor, P. A. and Skoglund, J.},
	month = sep,
	year = {2014},
	note = {tex.days= 1
tex.owner= dje11},
	keywords = {Dereverberation, Linear Prediction},
}

The SMERSH algorithm is a physiologically-motivated approach to low-complexity speech dereverberation. It employs multichannel linear prediction to obtain a reverberant residual signal and subsequent larynx-synchronous temporal averaging to attenuate the reverberation during voiced speech. Experimental results suggest the method is successful but, to date, no detailed analysis of the theoretical basis of the larynx-synchronous averaging has been undertaken. In this paper the SMERSH algorithm is reviewed before focussing on the theoretical basis of its approach. We show that the amount of dereverberation that can be achieved depends on the coherence of reverberation between frames. Simulations show that the extent of dereverberation increases with reverberation time and give an insight into the tradeoff between dereverberation and speech distortion.

@inproceedings{Evers2014,
	address = {Nice, France},
	title = {Multiple source localisation in the spherical harmonic domain},
	booktitle = {{IWAENC}},
	author = {Evers, C. and Moore, A. H. and Naylor, P. A.},
	month = jul,
	year = {2014},
	note = {tex.owner= cevers},
}

@inproceedings{Moore2014,
	title = {Room identification using roomprints},
	url = {http://www.aes.org/e-lib/browse.cfm?elib=17319},
	booktitle = {{AES}\_FORENSIC},
	author = {Moore, A. H. and Brookes, M. and Naylor, P. A.},
	month = jun,
	year = {2014},
	note = {tex.owner= dje11},
}

@inproceedings{Moore2013a,
	address = {New Paltz, NY, USA},
	title = {Roomprints for forensic audio},
	url = {http://www.commsp.ee.ic.ac.uk/~sap/uploads/publications/Moore2013a.pdf},
	booktitle = {{WASPAA}},
	author = {Moore, A. H. and Brookes, M. and Naylor, P. A.},
	year = {2013},
	note = {tex.owner= amoore1},
}

@inproceedings{Moore2013,
	address = {Marrakech, Morocco},
	title = {Room geometry estimation from a single channel acoustic impulse response},
	url = {http://www.commsp.ee.ic.ac.uk/~sap/uploads/publications/Moore2013.pdf},
	booktitle = {{EUSIPCO}},
	publisher = {IEEE},
	author = {Moore, Alastair H. and Brookes, Mike and Naylor, Patrick A.},
	month = sep,
	year = {2013},
	note = {tex.owner= amoore1},
	keywords = {TOA, acoustic impulse response, geometry estimation, room identification, time of arrival},
}

@article{Moore2010,
	title = {An initial validation of individualized crosstalk cancellation filters for binaural perceptual experiments},
	volume = {58},
	url = {http://www.aes.org/e-lib/browse.cfm?elib=15240},
	number = {1/2},
	urldate = {2017-01-25},
	journal = {J\_AES},
	author = {Moore, Alastair H. and Tew, Anthony I. and Nicol, Rozenn},
	year = {2010},
	pages = {36--45},
}

@phdthesis{zotero-null-22812,
	address = {York, UK},
	type = {phdthesis},
	title = {Towards the perception of externalised auditory images using binaural technology},
	abstract = {Binaural technology attempts to create auditory images at particular spatial locations by reproducing the localisation cues experienced during normal listening. However, virtual sound sources are often perceived very close to or inside the head, especially when the intended location is in front of the listener. The reasons for this are not well understood. This thesis documents the development and testing of a system which can produce frontally externalised images under controlled conditions. As a result, many of the factors believed to affect externalisation can now be systematically investigated.
To be considered adequate a virtual source should be perceptually indistinguishable from a real sound source in a blind comparison. Previous studies have used headphones to deliver the binaural stimuli, but this compromises the fidelity of the real source. Using loudspeakers to deliver the binaural stimuli allows the real source to be perceived normally, but requires an additional stage of signal processing to overcome the acoustic crosstalk.
Three alternative approaches to designing crosstalk cancellation filters were implemented and tested using simulations. The fast deconvolution with frequency-dependent regularisation technique was shown to be the most promising and acoustic tests verified its effectiveness.
A complete system using probe microphones was developed, which allowed the in situ calibration of the binaural synthesis and crosstalk cancellation filters. In two formal listening tests, listeners were required to detect differences between a virtual sound source reproduced using loudspeakers placed at ±90◦ and a real (reference) sound source located to the front (0◦). The results of both experiments showed that, provided the head was kept still, the system was exceptionally effective with listeners generally being unable to detect any differences. A further listening test found that when the system was used to simulate headphone listening the auditory image collapsed into the back of the head, as would be expected.},
	school = {University of York},
	author = {Moore, Alastair H.},
	year = {2009},
}

Binaural technology attempts to create auditory images at particular spatial locations by reproducing the localisation cues experienced during normal listening. However, virtual sound sources are often perceived very close to or inside the head, especially when the intended location is in front of the listener. The reasons for this are not well understood. This thesis documents the development and testing of a system which can produce frontally externalised images under controlled conditions. As a result, many of the factors believed to affect externalisation can now be systematically investigated. To be considered adequate a virtual source should be perceptually indistinguishable from a real sound source in a blind comparison. Previous studies have used headphones to deliver the binaural stimuli, but this compromises the fidelity of the real source. Using loudspeakers to deliver the binaural stimuli allows the real source to be perceived normally, but requires an additional stage of signal processing to overcome the acoustic crosstalk. Three alternative approaches to designing crosstalk cancellation filters were implemented and tested using simulations. The fast deconvolution with frequency-dependent regularisation technique was shown to be the most promising and acoustic tests verified its effectiveness. A complete system using probe microphones was developed, which allowed the in situ calibration of the binaural synthesis and crosstalk cancellation filters. In two formal listening tests, listeners were required to detect differences between a virtual sound source reproduced using loudspeakers placed at ±90◦ and a real (reference) sound source located to the front (0◦). The results of both experiments showed that, provided the head was kept still, the system was exceptionally effective with listeners generally being unable to detect any differences. A further listening test found that when the system was used to simulate headphone listening the auditory image collapsed into the back of the head, as would be expected.

@inproceedings{Beeson2008,
	title = {{RenderAIR}–{Room} {Acoustics} {Simulation} {Using} a {Hybrid} {Digital} {Waveguide} {Mesh} {Approach}},
	url = {http://www.aes.org/e-lib/browse.cfm?elib=14559},
	urldate = {2017-01-25},
	booktitle = {{AES}},
	publisher = {Audio Engineering Society},
	author = {Beeson, Mark and Moore, Alastair and Murphy, Damian and Shelley, Simon and Southern, Alexander},
	year = {2008},
}

@inproceedings{Murphy2008,
	title = {Hybrid room impulse response synthesis in digital waveguide mesh based room acoustics simulation},
	url = {http://core.ac.uk/download/pdf/21721150.pdf},
	urldate = {2017-01-25},
	booktitle = {{DAFX}},
	author = {Murphy, Damian and Beeson, Mark and Shelley, Simon and Moore, Alastair and Southern, Alex},
	year = {2008},
	pages = {129--136},
}

@inproceedings{Moore2007,
	title = {Headphone transparification: {A} novel method for investigating the externalization of binaural sounds},
	shorttitle = {Headphone {Transparification}},
	url = {http://www.aes.org/e-lib/online/browse.cfm?elib=14224},
	urldate = {2017-01-25},
	booktitle = {{AES}},
	publisher = {Audio Engineering Society},
	author = {Moore, Alastair H. and Tew, Anthony I. and Nicol, Rozenn},
	year = {2007},
}