论文信息 - A Novel Noise Robust Front-End Using First Order VTS in Construction of Mel-Warped Wiener Filter

A Novel Noise Robust Front-End Using First Order VTS in Construction of Mel-Warped Wiener Filter

In this paper, we first review two approaches in the context of robust recognition, e.g. speech enhancement based two-stage mel-warp Wiener filtering (MWF) (A. Agarwal and Y.M. Cheng, 1999) and first-order vector Taylor series (VTS) (P.J. Moreno et al., 1996) compensation in log power spectrum, which are widely used. A new noise robust front-end is proposed, in which VTS compensation derived statistics are used to construct the mel-warped Wiener filter. We will show that this noise robust front end is superior. The experiments results prove that our proposed method does show significant improvement over VTS and MWF

Peng Li | Bo Xu | Zhuo Wang | Peng Ding | Mu Su

[1] Richard M. Stern,et al. A vector Taylor series approach for environment-independent speech recognition , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[2] Jasha Droppo,et al. A noise-robust ASR front-end using Wiener filter constructed from MMSE estimation of clean speech and noise , 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

[3] Li Deng,et al. Large-vocabulary speech recognition under adverse acoustic environments , 2000, INTERSPEECH.

[4] Guo-Hong Ding,et al. Exploring high-performance speech recognition in noisy environments using high-order taylor series expansion , 2004, INTERSPEECH.

[5] Herman J. M. Steeneken,et al. Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems , 1993, Speech Commun..

[6] Bo Xu,et al. Update progress of Sinohear: advanced Mandarin LVCSR system at NLPR , 2000, INTERSPEECH.

[7] Anshu Agarwal,et al. TWO-STAGE MEL-WARPED WIENER FILTER FOR ROBUST SPEECH RECOGNITION , 1999 .