A bidirectional target-filtering model of speech coarticulation and reduction: two-stage implementation for phonetic recognition

By Li Deng, Dong Yu, A. Acero. 2006

27 citations recorded by the source corpus.

A structured generative model of speech coarticulation and reduction is described with a novel two-stage implementation. At the first stage, the dynamics of formants or vocal tract resonances (VTRs) in fluent speech is generated using prior information of resonance targets in the phone sequence, in absence of acoustic data. Bidirectional temporal filtering with finite-impulse response (FIR) is applied to the segmental target sequence as the FIR filter's input, where forward filtering produces anticipatory coarticulation and backward filtering produces regressive coarticulation. The filtering process is shown also to result in realistic resonance-frequency undershooting or reduction for fast-rate and low-effort speech in a contextually assimilated manner. At the second stage, the dynamics of speech cepstra are predicted analytically based on the FIR-filtered and speaker-adapted VTR targets, and the prediction residuals are modeled by Gaussian random variables with trainable parameters. The combined system of these two stages, thus, generates correlated and causally related VTR and cepstral dynamics, where phonetic reduction is represented explicitly in the hidden resonance space and implicitly in the observed cepstral space. We present details of model simulation demonstrating quantitative effects of speaking rate and segment duration on the magnitude of reduction, agreeing closely with experimental measurement results in the acoustic-phonetic literature. This two-stage model is implemented and applied to the TIMIT phonetic recognition task. Using the N-best (N=2000) rescoring paradigm, the new model, which contains only context-independent parameters, is shown to significantly reduce the phone error rate of a standard hidden Markov model (HMM) system under the same experimental conditions.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Li Deng
2. Dong Yu
3. Yoshua Bengio
4. Shizhen Wang
5. Jinyu Li
6. Xiaodong He
7. Jianfeng Gao
8. Frank Torsten Bernd Seide

In Experimental and Cognitive Psychology

1. Dong Yu
2. Shizhen Wang
3. Li Deng

In Signal Processing

1. Li Deng
2. Dong Yu
3. Shizhen Wang
4. Jinyu Li
5. Yoshua Bengio
6. Yifan Gong
7. Frank Torsten Bernd Seide
8. S. Renals

Citations in the corpus

• Structured speech modeling (2006, unknown): “Another parametric form of the hidden trajectory, which also satisfies these two constraints has been developed more recently [8], [10], [11] based on finite-impulse response (FIR) filtering of VTR target sequences.”
• Learning in the Deep-Structured Conditional Random Fields (2009, background): “Allowing for long-span features can be helpful for speech recognition [20] [21][22][23] tasks.”
• Sequential Labeling Using Deep-Structured Conditional Random Fields (2010, methodology): “Following the earlier work [4], [7], [16], [18] on this task, the annotated ads are divided into a 102-ads training set, a 100-ads development set, and a 100-ads test set.”