@InProceedings{8081516,
  author = {L. Shi and J. K. Nielsen and J. R. Jensen and M. G. Christensen},
  booktitle = {2017 25th European Signal Processing Conference (EUSIPCO)},
  title = {A variational EM method for pole-zero modeling of speech with mixed block sparse and Gaussian excitation},
  year = {2017},
  pages = {1784-1788},
  abstract = {The modeling of speech can be used for speech synthesis and speech recognition. We present a speech analysis method based on pole-zero modeling of speech with mixed block sparse and Gaussian excitation. By using a pole-zero model, instead of the all-pole model, a better spectral fitting can be expected. Moreover, motivated by the block sparse glottal flow excitation during voiced speech and the white noise excitation for unvoiced speech, we model the excitation sequence as a combination of block sparse signals and white noise. A variational EM (VEM) method is proposed for estimating the posterior PDFs of the block sparse residuals and point estimates of modelling parameters within a sparse Bayesian learning framework. Compared to conventional pole-zero and all-pole based methods, experimental results show that the proposed method has lower spectral distortion and good performance in reconstructing of the block sparse excitation.},
  keywords = {Bayes methods;expectation-maximisation algorithm;poles and zeros;speech processing;speech recognition;speech synthesis;white noise;expectation-maximization algorithm;sparse Bayesian learning framework;block sparse residuals;block sparse signals;excitation sequence;unvoiced speech;white noise excitation;voiced speech;glottal flow excitation;all-pole model;speech analysis method;speech synthesis;Gaussian excitation;mixed block sparse;pole-zero modeling;variational EM method;block sparse excitation;all-pole based methods;Speech;Analytical models;Probability density function;White noise;Estimation;Speech analysis;Europe},
  doi = {10.23919/EUSIPCO.2017.8081516},
  issn = {2076-1465},
  month = {Aug},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2017/papers/1570343400.pdf},
}

{"_id":"3QaPoxQyGb7NvsThF","bibbaseid":"shi-nielsen-jensen-christensen-avariationalemmethodforpolezeromodelingofspeechwithmixedblocksparseandgaussianexcitation-2017","authorIDs":[],"author_short":["Shi, L.","Nielsen, J. K.","Jensen, J. R.","Christensen, M. G."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["L."],"propositions":[],"lastnames":["Shi"],"suffixes":[]},{"firstnames":["J.","K."],"propositions":[],"lastnames":["Nielsen"],"suffixes":[]},{"firstnames":["J.","R."],"propositions":[],"lastnames":["Jensen"],"suffixes":[]},{"firstnames":["M.","G."],"propositions":[],"lastnames":["Christensen"],"suffixes":[]}],"booktitle":"2017 25th European Signal Processing Conference (EUSIPCO)","title":"A variational EM method for pole-zero modeling of speech with mixed block sparse and Gaussian excitation","year":"2017","pages":"1784-1788","abstract":"The modeling of speech can be used for speech synthesis and speech recognition. We present a speech analysis method based on pole-zero modeling of speech with mixed block sparse and Gaussian excitation. By using a pole-zero model, instead of the all-pole model, a better spectral fitting can be expected. Moreover, motivated by the block sparse glottal flow excitation during voiced speech and the white noise excitation for unvoiced speech, we model the excitation sequence as a combination of block sparse signals and white noise. A variational EM (VEM) method is proposed for estimating the posterior PDFs of the block sparse residuals and point estimates of modelling parameters within a sparse Bayesian learning framework. Compared to conventional pole-zero and all-pole based methods, experimental results show that the proposed method has lower spectral distortion and good performance in reconstructing of the block sparse excitation.","keywords":"Bayes methods;expectation-maximisation algorithm;poles and zeros;speech processing;speech recognition;speech synthesis;white noise;expectation-maximization algorithm;sparse Bayesian learning framework;block sparse residuals;block sparse signals;excitation sequence;unvoiced speech;white noise excitation;voiced speech;glottal flow excitation;all-pole model;speech analysis method;speech synthesis;Gaussian excitation;mixed block sparse;pole-zero modeling;variational EM method;block sparse excitation;all-pole based methods;Speech;Analytical models;Probability density function;White noise;Estimation;Speech analysis;Europe","doi":"10.23919/EUSIPCO.2017.8081516","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2017/papers/1570343400.pdf","bibtex":"@InProceedings{8081516,\n author = {L. Shi and J. K. Nielsen and J. R. Jensen and M. G. Christensen},\n booktitle = {2017 25th European Signal Processing Conference (EUSIPCO)},\n title = {A variational EM method for pole-zero modeling of speech with mixed block sparse and Gaussian excitation},\n year = {2017},\n pages = {1784-1788},\n abstract = {The modeling of speech can be used for speech synthesis and speech recognition. We present a speech analysis method based on pole-zero modeling of speech with mixed block sparse and Gaussian excitation. By using a pole-zero model, instead of the all-pole model, a better spectral fitting can be expected. Moreover, motivated by the block sparse glottal flow excitation during voiced speech and the white noise excitation for unvoiced speech, we model the excitation sequence as a combination of block sparse signals and white noise. A variational EM (VEM) method is proposed for estimating the posterior PDFs of the block sparse residuals and point estimates of modelling parameters within a sparse Bayesian learning framework. Compared to conventional pole-zero and all-pole based methods, experimental results show that the proposed method has lower spectral distortion and good performance in reconstructing of the block sparse excitation.},\n keywords = {Bayes methods;expectation-maximisation algorithm;poles and zeros;speech processing;speech recognition;speech synthesis;white noise;expectation-maximization algorithm;sparse Bayesian learning framework;block sparse residuals;block sparse signals;excitation sequence;unvoiced speech;white noise excitation;voiced speech;glottal flow excitation;all-pole model;speech analysis method;speech synthesis;Gaussian excitation;mixed block sparse;pole-zero modeling;variational EM method;block sparse excitation;all-pole based methods;Speech;Analytical models;Probability density function;White noise;Estimation;Speech analysis;Europe},\n doi = {10.23919/EUSIPCO.2017.8081516},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2017/papers/1570343400.pdf},\n}\n\n","author_short":["Shi, L.","Nielsen, J. K.","Jensen, J. R.","Christensen, M. G."],"key":"8081516","id":"8081516","bibbaseid":"shi-nielsen-jensen-christensen-avariationalemmethodforpolezeromodelingofspeechwithmixedblocksparseandgaussianexcitation-2017","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2017/papers/1570343400.pdf"},"keyword":["Bayes methods;expectation-maximisation algorithm;poles and zeros;speech processing;speech recognition;speech synthesis;white noise;expectation-maximization algorithm;sparse Bayesian learning framework;block sparse residuals;block sparse signals;excitation sequence;unvoiced speech;white noise excitation;voiced speech;glottal flow excitation;all-pole model;speech analysis method;speech synthesis;Gaussian excitation;mixed block sparse;pole-zero modeling;variational EM method;block sparse excitation;all-pole based methods;Speech;Analytical models;Probability density function;White noise;Estimation;Speech analysis;Europe"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2017url.bib","creationDate":"2021-02-13T16:38:25.701Z","downloads":0,"keywords":["bayes methods;expectation-maximisation algorithm;poles and zeros;speech processing;speech recognition;speech synthesis;white noise;expectation-maximization algorithm;sparse bayesian learning framework;block sparse residuals;block sparse signals;excitation sequence;unvoiced speech;white noise excitation;voiced speech;glottal flow excitation;all-pole model;speech analysis method;speech synthesis;gaussian excitation;mixed block sparse;pole-zero modeling;variational em method;block sparse excitation;all-pole based methods;speech;analytical models;probability density function;white noise;estimation;speech analysis;europe"],"search_terms":["variational","method","pole","zero","modeling","speech","mixed","block","sparse","gaussian","excitation","shi","nielsen","jensen","christensen"],"title":"A variational EM method for pole-zero modeling of speech with mixed block sparse and Gaussian excitation","year":2017,"dataSources":["2MNbFYjMYTD6z7ExY","uP2aT6Qs8sfZJ6s8b"]}