Title :
An expectation maximization approach for formant tracking using a parameter-free non-linear predictor
Author :
Bazzi, Issam ; Acero, Alex ; Deng, Li
Author_Institution :
Microsoft Res., Redmond, WA, USA
Abstract :
This paper presents a new approach for formant tracking using a parameter-free non-linear predictor that maps formant frequencies and bandwidths into the acoustic feature space. The approach relies on decomposing the speech signal into two components: the first component captures the mapping between formants and acoustic observations, while the second component is intended to capture the residual in the signal. We build the mapping by quantizing the formant space and creating a predictor codebook. Formant tracking is achieved by: (1) EM training of the parameters of the residual component, and (2) searching the predictor codebook for the best formant values. We explore both MAP and MMSE methods for performing formant tracking with the proposed approach. Furthermore, we impose first order continuity constraints on formant trajectories, and use Viterbi search to perform formant tracking. We present formant tracking results on data from the Switchboard corpus.
Keywords :
least mean squares methods; maximum likelihood estimation; nonlinear estimation; optimisation; search problems; speech processing; speech recognition; table lookup; EM training; MAP method; MMSE; Switchboard corpus; Viterbi search; acoustic feature space; acoustic observations; expectation maximization approach; first order continuity constraints; formant frequencies; formant tracking; formant trajectories; mapping; parameter-free nonlinear predictor; predictor codebook; quantization; residual capture; speech signal decomposition; Bandwidth; Linear predictive coding; Mel frequency cepstral coefficient; Nonlinear acoustics; Predictive models; Signal mapping; Speech analysis; Speech recognition; Trajectory; Video recording;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on
Print_ISBN :
0-7803-7663-3
DOI :
10.1109/ICASSP.2003.1198818