The ACE Challenge - corpus description and performance evaluation

The ACE Challenge - corpus description and performance evaluation. Eaton, J., Gaubitch, N. D., Moore, A. H., & Naylor, P. A. In WASPAA, New Paltz, NY, USA, 2015. tex.day= 18-21 tex.owner= dje11
doi abstract bibtex

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{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},
}

Downloads: 0

{"_id":"2facENwnvNdLdiFCd","bibbaseid":"eaton-gaubitch-moore-naylor-theacechallengecorpusdescriptionandperformanceevaluation-2015","downloads":0,"creationDate":"2017-01-06T10:17:23.326Z","title":"The ACE Challenge - corpus description and performance evaluation","author_short":["Eaton, J.","Gaubitch, N. D.","Moore, A. H.","Naylor, P. A."],"year":2015,"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/3646722/collections/T2R9K7BX/items?key=BOpOAr8MeAOlvK9qDoPzmAHq&format=bibtex&limit=100","bibdata":{"bibtype":"inproceedings","type":"inproceedings","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":[{"propositions":[],"lastnames":["Eaton"],"firstnames":["J."],"suffixes":[]},{"propositions":[],"lastnames":["Gaubitch"],"firstnames":["N.","D."],"suffixes":[]},{"propositions":[],"lastnames":["Moore"],"firstnames":["A.","H."],"suffixes":[]},{"propositions":[],"lastnames":["Naylor"],"firstnames":["P.","A."],"suffixes":[]}],"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","bibtex":"@inproceedings{Eaton2015a,\n\taddress = {New Paltz, NY, USA},\n\ttitle = {The {ACE} {Challenge} - corpus description and performance evaluation},\n\tdoi = {10.1109/WASPAA.2015.7336912},\n\tabstract = {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.},\n\tbooktitle = {{WASPAA}},\n\tauthor = {Eaton, J. and Gaubitch, N. D. and Moore, A. H. and Naylor, P. A.},\n\tyear = {2015},\n\tnote = {tex.day= 18-21\ntex.owner= dje11},\n\tkeywords = {Acoustics, Arrays, Buildings, Frequency measurement, Microphones, Noise measurement, Speech, acoustic impulse response, speech dereverberation, speech enhancement},\n}\n\n","author_short":["Eaton, J.","Gaubitch, N. D.","Moore, A. H.","Naylor, P. A."],"key":"Eaton2015a","id":"Eaton2015a","bibbaseid":"eaton-gaubitch-moore-naylor-theacechallengecorpusdescriptionandperformanceevaluation-2015","role":"author","urls":{},"keyword":["Acoustics","Arrays","Buildings","Frequency measurement","Microphones","Noise measurement","Speech","acoustic impulse response","speech dereverberation","speech enhancement"],"metadata":{"authorlinks":{"moore, a":"https://bibbase.org/show?bib=https%3A%2F%2Fapi.zotero.org%2Fusers%2F3646722%2Fcollections%2FT2R9K7BX%2Fitems%3Fkey%3DBOpOAr8MeAOlvK9qDoPzmAHq%26format%3Dbibtex%26limit%3D100"}},"downloads":0},"search_terms":["ace","challenge","corpus","description","performance","evaluation","eaton","gaubitch","moore","naylor"],"keywords":["acoustics","arrays","buildings","frequency measurement","microphones","noise measurement","speech","acoustic impulse response","speech dereverberation","speech enhancement"],"authorIDs":["X2bE5e9oADPNMPewb"],"dataSources":["6HSxAQZbW5XsjnSpj","XnMG7GzeqgE96krqB"]}