Permutation invariant training of deep models for speaker-independent multi-talker speech separation
Top Cited Papers
- 1 March 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Mechanical Engineering Journal
- p. 241-245
Abstract
We propose a novel deep learning training criterion, named permutation invariant training (PIT), for speaker independent multi-talker speech separation, commonly known as the cocktail-party problem. Different from the multi-class regression technique and the deep clustering (DPCL) technique, our novel approach minimizes the separation error directly. This strategy effectively solves the long-lasting label permutation problem, that has prevented progress on deep learning based techniques for speech separation. We evaluated PIT on the WSJ0 and Danish mixed-speech separation tasks and found that it compares favorably to non-negative matrix factorization (NMF), computational auditory scene analysis (CASA), and DPCL and generalizes well over unseen speakers and languages. Since PIT is simple to implement and can be easily integrated and combined with other advanced techniques, we believe improvements built upon PIT can eventually solve the cocktail-party problem.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR2015
- Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Deep Neural Networks for Single-Channel Multi-Talker Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- On Training Targets for Supervised Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Monaural speech separation and recognition challengeComputer Speech & Language, 2010
- Monaural Speech Separation using Source-Adapted Models2007
- Some Experiments on the Recognition of Speech, with One and with Two EarsThe Journal of the Acoustical Society of America, 1953
- Laws of organization in perceptual forms.1938