Continuous Speech Separation with Conformer
arXiv:2008.05773
Abstract
Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and conformer in lieu of recurrent neural networks in the separation system, as we believe capturing global information with the self-attention based method is crucial for the speech separation. Evaluating on the LibriCSS dataset, the conformer separation model achieves state of the art results, with a relative 23.5% word error rate (WER) reduction from bi-directional LSTM (BLSTM) in the utterance-wise evaluation and a 15.4% WER reduction in the continuous evaluation.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Decoupled Weight Decay Regularization
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- Conformer: Convolution-augmented Transformer for Speech Recognition
- Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks
- CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings
- Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation
- LaFurca: Iterative Refined Speech Separation Based on Context-Aware Dual-Path Parallel Bi-LSTM
- Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
Cited by in corpus (7)
- A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection
- Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020
- Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
- TransMask: A Compact and Fast Speech Separation Model Based on Transformer
- MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation
- Investigation of Practical Aspects of Single Channel Speech Separation for ASR
- Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation