Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription

Abstract

While end-to-end ASR systems have proven competitive with the conventional hybrid approach, they are prone to accuracy degradation when it comes to noisy and low-resource conditions. In this paper, we argue that, even in such difficult cases, some end-to-end approaches show performance close to the hybrid baseline. To demonstrate this, we use the CHiME-6 Challenge data as an example of challenging environments and noisy conditions of everyday speech. We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures. We also provide a comparison of acoustic features and speech enhancements. Besides, we evaluate the effectiveness of neural network language models for hypothesis re-scoring in low-resource conditions. Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline. With the Guided Source Separation based training data augmentation, this approach outperforms the hybrid baseline system by 2.7% WER abs. and the end-to-end system best known before by 25.7% WER abs.

arXiv commentAccepted by Interspeech 2020

References in corpus (10)

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Sequence Transduction with Recurrent Neural Networks
• A Comparative Study on Transformer vs RNN in Speech Applications
• Improved training of end-to-end attention models for speech recognition
• End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
• CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings
• Self-Attention Transducers for End-to-End Speech Recognition
• Transformer-Transducer: End-to-End Speech Recognition with Self-Attention
• RNN-T For Latency Controlled ASR With Improved Beam Search
• An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions

Cited by in corpus (6)

• SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
• A New Training Pipeline for an Improved Neural Transducer
• You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation
• Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition
• The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans
• Data Augmentation Methods for End-to-end Speech Recognition on Distant-Talk Scenarios