{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/emformer-efficient-memory-transformer-based","title":"Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition","arxiv_id":"2010.10759","date":"2020-10-21","proceeding":null,"authors":["Yangyang Shi","Yongqiang Wang","Chunyang Wu","Ching-Feng Yeh","Julian Chan","Frank Zhang","Duc Le","Mike Seltzer"],"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.","url_abs":"https://arxiv.org/abs/2010.10759v4","url_pdf":"https://arxiv.org/pdf/2010.10759v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"emformer-efficient-memory-transformer-based","repo_url":"https://github.com/George0828Zhang/simulst","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.10759","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}