A Speaker-Dependent Approach to Separation of Far-Field Multi-Talker Microphone Array Speech for Front-End Processing in the CHiME-5 Challenge
- 3 June 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 13 (4) , 827-840
Abstract
We propose a novel speaker-dependent speech separation framework for the challenging CHiME-5 acoustic environments, exploiting advantages of both deep learning based and conventional preprocessing techniques to prepare data effectively for separating target speech from multi-talker mixed speech collected with multiple microphone arrays. First, a series of multi-channel operations is conducted to reduce existing reverberation and noise, and a single-channel deep learning based speech enhancement model is used to predict speech presence probabilities. Next, a two-stage supervised speech separation approach, using oracle speaker diarization information from CHiME-5, is proposed to separate speech of a target speaker from interference speakers in mixed speech. Given a set of three estimated masks of the background noise, the target speaker and the interference speakers from single-channel speech enhancement and separation models, a complex Gaussian mixture model (CGMM) based generalized eigenvalue (GEV) beamformer is then used for enhancing the signal at the reference array while avoiding the speaker permutation issue. Furthermore, the proposed front-end can generate a large variety of processed data for an ensemble of speech recognition results. Experiments on the development set have shown that the proposed two-stage approach can yield significant improvements of recognition performance over the official baseline system and achieved top accuracies in all four competing evaluation categories among all systems submitted to the CHiME-5 Challenge.Keywords
Funding Information
- National Key R&D Program of China (2017YFB1002202)
- National Natural Science Foundation of China (61671422, U1613211)
- Key Science and Technology Project of Anhui Province (17030901005)
- Tencent
This publication has 58 references indexed in Scilit:
- The PASCAL CHiME speech separation and recognition challengeComputer Speech & Language, 2013
- Time-Frequency Masking for Speech Separation and Its Potential for Hearing Aid DesignTrends in Amplification, 2008
- Unleashing the killer corpus: experiences in creating the multi-everything AMI Meeting CorpusLanguage Resources and Evaluation, 2007
- Speech enhancement for non-stationary noise environmentsSignal Processing, 2001
- An approach to blind source separation based on temporal structure of speech signalsNeurocomputing, 2001
- Independent component analysis, A new concept?Signal Processing, 1994
- Robust adaptive beamformingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- Speech analysis/Synthesis based on a sinusoidal representationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986
- Speech enhancement using a minimum-mean square error short-time spectral amplitude estimatorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1984
- Some Experiments on the Recognition of Speech, with One and with Two EarsThe Journal of the Acoustical Society of America, 1953