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

arXiv: https://arxiv.org/abs/2010.10759 · HTML: https://mlsanity.com/paper/2010.10759/

## Key facts

- Cited by 113 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 30 of 113)

- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition](https://mlsanity.com/paper/2106.05933/) (2021)
- [SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts](https://mlsanity.com/paper/2105.03036/) (2021)
- [Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding](https://mlsanity.com/paper/2104.02138/) (2021)
- [Transformers in Speech Processing: A Survey](https://mlsanity.com/paper/2303.11607/) (2023)
- [Factorized Neural Transducer for Efficient Language Model Adaptation](https://mlsanity.com/paper/2110.01500/) (2021)
- [Towards measuring fairness in speech recognition: Fair-Speech dataset](https://mlsanity.com/paper/2408.12734/) (2024)
- [Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition](https://mlsanity.com/paper/2312.17279/) (2023)
- [Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric](https://mlsanity.com/paper/2110.05376/) (2021)
- [Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks](https://mlsanity.com/paper/2305.03101/) (2023)
- [Dissecting User-Perceived Latency of On-Device E2E Speech Recognition](https://mlsanity.com/paper/2104.02207/) (2021)
- [Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities](https://mlsanity.com/paper/2211.05756/) (2022)
- [Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time](https://mlsanity.com/paper/2406.09569/) (2024)
- [Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation](https://mlsanity.com/paper/2204.09595/) (2022)
- [STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining](https://mlsanity.com/paper/2207.05022/) (2022)
- [Variable Attention Masking for Configurable Transformer Transducer Speech Recognition](https://mlsanity.com/paper/2211.01438/) (2022)
- [XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaverse](https://mlsanity.com/paper/2211.08675/) (2022)
- [Towards Online Continuous Sign Language Recognition and Translation](https://mlsanity.com/paper/2401.05336/) (2024)
- [Model-Based Approach for Measuring the Fairness in ASR](https://mlsanity.com/paper/2109.09061/) (2021)
- [Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks](https://mlsanity.com/paper/2210.07499/) (2022)
- [Decoder-only Architecture for Streaming End-to-end Speech Recognition](https://mlsanity.com/paper/2406.16107/) (2024)
- [Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet](https://mlsanity.com/paper/2110.08352/) (2021)
- [Learning ASR pathways: A sparse multilingual ASR model](https://mlsanity.com/paper/2209.05735/) (2022)
- [Improving the fusion of acoustic and text representations in RNN-T](https://mlsanity.com/paper/2201.10240/) (2022)
- [Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation](https://mlsanity.com/paper/2204.08920/) (2022)
- [Improving Fairness and Robustness in End-to-End Speech Recognition through unsupervised clustering](https://mlsanity.com/paper/2306.06083/) (2023)
- [SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding](https://mlsanity.com/paper/2307.07421/) (2023)

## Abstract (arXiv)

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.