000165200 001__ 165200
000165200 005__ 20190316235102.0
000165200 02470 $$2ISI$$a000296062405217
000165200 037__ $$aCONF
000165200 245__ $$aSPARSE NON-NEGATIVE DECOMPOSITION OF SPEECH POWER SPECTRA FOR FORMANT TRACKING
000165200 269__ $$a2011
000165200 260__ $$bIeee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa$$c2011
000165200 336__ $$aConference Papers
000165200 490__ $$aInternational Conference on Acoustics Speech and Signal Processing ICASSP
000165200 520__ $$aMany works on speech processing have dealt with auto-regressive (AR) models for spectral envelope and formant frequency estimation, mostly focusing on the estimation of the AR parameters. However, it is also interesting to be able to directly estimate the formant frequencies, or equivalently the poles of the AR filter. To tackle this issue, we propose in this paper to decompose the signal onto several bases, one for each formant, taking advantage of recent works on nonnegative matrix factorization (NMF) for the estimation stage, further refined by sparsity and smoothness penalties. The results are encouraging, and the proposed system provides formant tracks which seem robust enough to be used in different applications such as phonetic analysis, emotion detection or as visual cue for computer-aided pronunciation training applications. The model can also be extended to deal with multiple-speaker signals.
000165200 6531_ $$aSpeech Analysis
000165200 6531_ $$aAutoregressive (AR) Model
000165200 6531_ $$aSource-Filter Model
000165200 6531_ $$aNon-negative Matrix Factorization
000165200 6531_ $$aSparse Decomposition
000165200 700__ $$0242943$$aDurrieu, Jean-Louis$$g202892
000165200 700__ $$0240323$$aThiran, Jean-Philippe$$g115534
000165200 7112_ $$aInternational Conference on Acoustics, Speech and Signal Processing (ICASSP)$$cPrague, Czech Republic$$dMay 22-27, 2011
000165200 773__ $$tProceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
000165200 8564_ $$s240440$$uhttps://infoscience.epfl.ch/record/165200/files/durrieuThiran-2011icassp-R2.pdf$$zn/a
000165200 909C0 $$0252394$$pLTS5$$xU10954
000165200 909CO $$ooai:infoscience.tind.io:165200$$pconf$$pSTI$$qGLOBAL_SET
000165200 917Z8 $$x202892
000165200 917Z8 $$x115534
000165200 937__ $$aEPFL-CONF-165200
000165200 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000165200 980__ $$aCONF