Robust MVDR beamforming using time-frequency masks for online/offline ASR in noise
Top Cited Papers
- 1 March 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5210-5214
Abstract
This paper considers acoustic beamforming for noise robust automatic speech recognition (ASR). A beamformer attenuates background noise by enhancing sound components coming from a direction specified by a steering vector. Hence, accurate steering vector estimation is paramount for successful noise reduction. Recently, a beamforming approach was proposed that employs time-frequency masks. In the speech recognition system we submitted to the CHiME-3 Challenge, we employed a new form of this approach that uses a speech spectral model based on a complex Gaussian mixture model (CGMM) to estimate the time-frequency masks and the steering vector without providing technical details. This paper elaborates on this technique and examines its effectiveness for ASR. Experimental results show that the CGMM-based approach outperforms a recently proposed mask estimator based on a Watson mixture model. In addition, the CGMM-based approach is extended to an online speech enhancement scenario, which allows this technique to be used in an online recognition setup. This online version reduces the CHiME-3 evaluation error rate from 15.60% to 8.47%, which is a comparable improvement to that obtained by batch processing.Keywords
This publication has 20 references indexed in Scilit:
- The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices2015
- The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines2015
- Strategies for distant speech recognitionin reverberant environmentsEURASIP Journal on Advances in Signal Processing, 2015
- Deep Convolutional Neural Networks for Large-scale Speech TasksNeural Networks, 2015
- Relaxed disjointness based clustering for joint blind source separation and dereverberation2014
- Convolutional Neural Networks for Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Impact of single-microphone dereverberation on DNN-based meeting transcription systems2014
- Hybrid acoustic models for distant and multichannel large vocabulary speech recognition2013
- Blind Separation of Speech Mixtures via Time-Frequency MaskingIEEE Transactions on Signal Processing, 2004
- Robust Localization in Reverberant Rooms2001