Modeling temporal dependency for robust estimation of LP model parameters in speech enhancement
Refereed conference paper presented and published in conference proceedings


Full Text

Times Cited

Other information
AbstractThis paper presents a novel approach to robust estimation of linear prediction (LP) model parameters in the application of speech enhancement. The robustness stems from the use of prior knowledge on the clean speech and the interfering noise, which are represented by two separate codebooks of LP model parameters. We propose to model the temporal dependency between short-time model parameters with a composite hidden Markov model (HMM) that is constructed by combining the speech and the noise codebooks. Optimal speech model parameters are estimated from the HMM state sequence that best matches the input observation. To further improve the estimation accuracy, we propose to perform interpolation of multiple HMM state sequences such that the estimated speech parameters would not be limited by the codebook coverage. Experimental results demonstrate the benefits and effectiveness of temporal dependency modeling and states interpolation in improving the segmental signal-to-noise ratio, PESQ and spectral distortion of enhanced speech.
All Author(s) ListWong C.H., Lee T., Yeung Y.T., Ching P.C.
Name of Conference16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015
Start Date of Conference06/09/2015
End Date of Conference10/09/2015
Place of ConferenceDresden
Country/Region of ConferenceGermany
Detailed descriptionInternational Speech Communication Association
Year2015
Month1
Day1
Volume Number2015-January
Pages1730 - 1734
ISBN978-1-5108-1790-6
ISSN1990-9772
LanguagesEnglish-United Kingdom
KeywordsHidden Markov model (HMM), Linear predictive (LP) model parameters, Speech enhancement

Last updated on 2020-22-09 at 02:25