Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models

by   Thibault Doutre, et al.

Streaming end-to-end automatic speech recognition (ASR) systems are widely used in everyday applications that require transcribing speech to text in real-time. Their minimal latency makes them suitable for such tasks. Unlike their non-streaming counterparts, streaming models are constrained to be causal with no future context and suffer from higher word error rates (WER). To improve streaming models, a recent study [1] proposed to distill a non-streaming teacher model on unsupervised utterances, and then train a streaming student using the teachers' predictions. However, the performance gap between teacher and student WERs remains high. In this paper, we aim to close this gap by using a diversified set of non-streaming teacher models and combining them using Recognizer Output Voting Error Reduction (ROVER). In particular, we show that, despite being weaker than RNN-T models, CTC models are remarkable teachers. Further, by fusing RNN-T and CTC models together, we build the strongest teachers. The resulting student models drastically improve upon streaming models of previous work [1]: the WER decreases by 41 Spanish, 27


page 1

page 2

page 3

page 4


Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data

Streaming end-to-end automatic speech recognition (ASR) models are widel...

Two-Pass End-to-End ASR Model Compression

Speech recognition on smart devices is challenging owing to the small me...

Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer

The demand for fast and accurate incremental speech recognition increase...

Lifelong Generative Modeling

Lifelong learning is the problem of learning multiple consecutive tasks ...

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization

Streaming automatic speech recognition (ASR) aims to emit each hypothesi...

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions

In recent years, all-neural end-to-end approaches have obtained state-of...

Streaming parallel transducer beam search with fast-slow cascaded encoders

Streaming ASR with strict latency constraints is required in many speech...