ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition

Abstract

In this paper we present state-of-the-art (SOTA) performance on the LibriSpeech corpus with two novel neural network architectures, a multistream CNN for acoustic modeling and a self-attentive simple recurrent unit (SRU) for language modeling. In the hybrid ASR framework, the multistream CNN acoustic model processes an input of speech frames in multiple parallel pipelines where each stream has a unique dilation rate for diversity. Trained with the SpecAugment data augmentation method, it achieves relative word error rate (WER) improvements of 4% on test-clean and 14% on test-other. We further improve the performance via N-best rescoring using a 24-layer self-attentive SRU language model, achieving WERs of 1.75% on test-clean and 4.46% on test-other.

arXiv commentSubmitted to Interspeech 2020

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• The Microsoft 2017 Conversational Speech Recognition System
• Achieving Human Parity in Conversational Speech Recognition
• Transformer-based Acoustic Modeling for Hybrid Speech Recognition
• End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
• The CAPIO 2017 Conversational Speech Recognition System
• ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
• Optimizing Speech Recognition For The Edge