DeepAI AI Chat
Log In Sign Up

Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition

by   Yangyang Shi, et al.

This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmented memory bank to reduce self-attention's computation complexity. A cache mechanism saves the computation for the key and value in self-attention for the left context. Emformer applies a parallelized block processing in training to support low latency models. We carry out experiments on benchmark LibriSpeech data. Under average latency of 960 ms, Emformer gets WER 2.50% on test-clean and 5.62% on test-other. Comparing with a strong baseline augmented memory transformer (AM-TRF), Emformer gets 4.6 folds training speedup and 18% relative real-time factor (RTF) reduction in decoding with relative WER reduction 17% on test-clean and 9% on test-other. For a low latency scenario with an average latency of 80 ms, Emformer achieves WER 3.01% on test-clean and 7.09% on test-other. Comparing with the LSTM baseline with the same latency and model size, Emformer gets relative WER reduction 9% and 16% on test-clean and test-other, respectively.


page 1

page 2

page 3

page 4


Dynamic Latency for CTC-Based Streaming Automatic Speech Recognition With Emformer

An inferior performance of the streaming automatic speech recognition mo...

Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution

This paper improves the streaming transformer transducer for speech reco...

Low latency transformers for speech processing

The transformer is a widely-used building block in modern neural network...

Super-Human Performance in Online Low-latency Recognition of Conversational Speech

Achieving super-human performance in recognizing human speech has been a...

Latency-Controlled Neural Architecture Search for Streaming Speech Recognition

Recently, neural architecture search (NAS) has attracted much attention ...

Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency Detection

In modern interactive speech-based systems, speech is consumed and trans...