The reviewed record of science sign in
Pith

arxiv: 2010.10759 · v4 · pith:FAF4VSSG · submitted 2020-10-21 · cs.SD · cs.CL· cs.LG· eess.AS

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:FAF4VSSGrecord.jsonopen to challenge →

classification cs.SD cs.CLcs.LGeess.AS
keywords emformerlatencymemorytest-cleantest-othergetsreductionrelative
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.