{"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/trimtail-low-latency-streaming-asr-with","title":"TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty","arxiv_id":"2211.00522","date":"2022-11-01","proceeding":null,"authors":["Xingchen Song","Di wu","Zhiyong Wu","BinBin Zhang","Yuekai Zhang","Zhendong Peng","Wenpeng Li","Fuping Pan","Changbao Zhu"],"abstract":"In this paper, we present TrimTail, a simple but effective emission regularization method to improve the latency of streaming ASR models. The core idea of TrimTail is to apply length penalty (i.e., by trimming trailing frames, see Fig. 1-(b)) directly on the spectrogram of input utterances, which does not require any alignment. We demonstrate that TrimTail is computationally cheap and can be applied online and optimized with any training loss or any model architecture on any dataset without any extra effort by applying it on various end-to-end streaming ASR networks either trained with CTC loss [1] or Transducer loss [2]. We achieve 100 $\\sim$ 200ms latency reduction with equal or even better accuracy on both Aishell-1 and Librispeech. Moreover, by using TrimTail, we can achieve a 400ms algorithmic improvement of User Sensitive Delay (USD) with an accuracy loss of less than 0.2.","url_abs":"https://arxiv.org/abs/2211.00522v2","url_pdf":"https://arxiv.org/pdf/2211.00522v2.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":"trimtail-low-latency-streaming-asr-with","repo_url":"https://github.com/mobvoi/wenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"ctc-loss","method_name":"CTC Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.00522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00522"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mobvoi/wenet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"listed":{"samples":5,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bf04ce1117479646","entry":"get_frames_timestamp","repo":"mobvoi/wenet","repo_kind":"listed","path":"wenet/bin/alignment.py","file_url":"https://github.com/mobvoi/wenet/blob/HEAD/wenet/bin/alignment.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bf04ce1117479646"}},{"code_sha256_prefix":"0562154e6c98265d","entry":"to_numpy","repo":"mobvoi/wenet","repo_kind":"listed","path":"wenet/bin/export_onnx_cpu.py","file_url":"https://github.com/mobvoi/wenet/blob/HEAD/wenet/bin/export_onnx_cpu.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0562154e6c98265d"}},{"code_sha256_prefix":"03a5062a6ac43d6d","entry":"to_numpy","repo":"mobvoi/wenet","repo_kind":"listed","path":"wenet/bin/export_onnx_gpu.py","file_url":"https://github.com/mobvoi/wenet/blob/HEAD/wenet/bin/export_onnx_gpu.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03a5062a6ac43d6d"}},{"code_sha256_prefix":"5de71dffdd6cdf93","entry":"download","repo":"mobvoi/wenet","repo_kind":"listed","path":"wenet/cli/hub.py","file_url":"https://github.com/mobvoi/wenet/blob/HEAD/wenet/cli/hub.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5de71dffdd6cdf93"}},{"code_sha256_prefix":"57793021e407cbaf","entry":"scripting","repo":"mobvoi/wenet","repo_kind":"listed","path":"wenet/bin/export_ipex.py","file_url":"https://github.com/mobvoi/wenet/blob/HEAD/wenet/bin/export_ipex.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57793021e407cbaf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}