Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition
Authors:
- 1 April 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5739-5743
Abstract
This paper describes a neural network approach to far-field speech separation using multiple microphones. Our proposed approach is speaker-independent and can learn to implicitly figure out the number of speakers constituting an input speech mixture. This is realized by utilizing the permutation invariant training (PIT) framework, which was recently proposed for single-microphone speech separation. In this paper, PIT is extended to effectively leverage multi-microphone input. It is also combined with beamforming for better recognition accuracy. The effectiveness of the proposed approach is investigated by multi-talker speech recognition experiments that use a large quantity of training data and encompass a range of mixing conditions. Our multi-microphone speech separation system significantly outperforms the single-microphone PIT. Several aspects of the proposed approach are experimentally investigated.Keywords
This publication has 18 references indexed in Scilit:
- A Maximum Likelihood Approach to Deep Neural Network Based Nonlinear Spectral Mapping for Single-Channel Speech Separation2017
- Large-Scale Domain Adaptation via Teacher-Student Learning2017
- Tight Integration of Spatial and Spectral Features for BSS with Deep Clustering Embeddings2017
- Binaural Reverberant Speech Separation Based on Deep Neural Networks2017
- Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural NetworksIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2017
- Deep attractor network for single-microphone speaker separation2017
- Improved MVDR Beamforming Using Single-Channel Mask Prediction Networks2016
- Deep clustering: Discriminative embeddings for segmentation and separation2016
- The NTT CHiME-3 system: Advances in speech enhancement and recognition for mobile multi-microphone devices2015
- Source counting in speech mixtures using a variational EM approach for complex WATSON mixture models2014