A state-space model with neural-network prediction for recovering vocal tract resonances in fluent speech from Mel-cepstral coefficients

Speech Communication

Volumn 48, Issue 8, 2006, Pages 971-988

  Togneri, Roberto ^a   Deng, Li ^b  

^a UNIVERSITY OF WESTERN AUSTRALIA   (Australia)

^b MICROSOFT RESEARCH   (United States)

Author keywords

Cepstra; EM algorithm; Hidden dynamics; Multi layer perceptron; Neural network; State space model; Tracking; Vocal tract resonance

Indexed keywords

ACOUSTIC MEASURING INSTRUMENTS; ALGORITHMS; KALMAN FILTERING; MAPPING; MATHEMATICAL MODELS; SPEECH PROCESSING; SPEECH SYNTHESIS;

CEPSTRA; EM ALGORITHM; HIDDEN DYNAMICS; MULTI-LAYER PERCEPTRON; STATE-SPACE MODEL; TRACKING; VOCAL TRACT RESONANCE (VTR) DYNAMICS;

NEURAL NETWORKS;

EID: 33745373922     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2006.01.001     Document Type: Article

References (17)

1. Allen J., Hunnicutt M.S., and Klatt D. From Text to Speech: The MITalk System (1987), Cambridge University Press, Cambridge, England
2. Delattre P.C., Liberman A.M., and Cooper F.S. Acoustic loci and transitional cues for consonants. J. Acoust. Soc. Amer. 27 (1955) 769-773
3. Deng L., and Ma J. Spontaneous speech recognition using a statistical coarticulatory model for the hidden vocal-tract-resonance dynamics. J. Acoust. Soc. Amer. 108 6 (2000) 3036-3048
4. Deng L., and O'Shaughnessy D. Speech Processing-A Dynamic and Optimization-Oriented Approach (2003), Marcel Dekker, New York
5. Deng, L., Bazzi, I., Acero, A., 2003. Tracking vocal tract resonances using an analytical nonlinear predictor and a target-guided temporal constraint. In: Proc. Eurospeech, pp. 73-76.
6. Foresee, F.D., Hagan, M.T., 1997. Gauss-Newton approximation to Bayesian regularization. In: Proc. Intern. Joint Conf. Neural Networks, pp. 1930-1935.
7. Haykin S. Neural Networks: A Comprehensive Foundation (1999), Prentice-Hall, Englewood Cliffs, NJ
8. Kewley-Port D. Time-varying features as correlates of place of articulation in stop consonants. J. Acoust. Soc. Amer. 73 (1983) 322-335
9. Klatt D. Software for a cascade/parallel formant synthesizer. J. Acoust. Soc. Amer. 67 (1980) 971-995
10. Kopec G. Formant tracking using HMMs and vector quantization. IEEE Trans. Acoust. Speech Signal Proc. 34 (1986) 709-729
11. McCandless S. An algorithm for automatic formant extraction using linear prediction spectra. IEEE Trans. Acoust. Speech Signal Proc. 22 (1974) 135-141
12. Seide, F., Zhou, J., Deng, L., 2003. Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM-MAP decoding and evaluation. In: Proc. ICASSP, pp. 748-751.
13. Sjolander K. Recent developments regarding the Wavesurfer speech tool (2002).
14. Stevens, K., 1993. Speech Synthesis with a formant synthesizer. Course Notes, Cambridge, MA, July.
15. Stevens K., and Bickley C. Constraints among parameters simplify control of Klatt formant synthesizer. J. Phonetics 19 (1991) 161-174
16. Togneri R., and Deng L. Joint state and parameter estimation for a target-directed nonlinear dynamic system model. IEEE Trans. Signal Process. 51 December (2003) 3061-3070
17. Zue V. Course Notes on Speech Spectrogram Reading (1991), MIT, Cambridge, MA