{"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/state-of-the-art-speech-recognition-using","title":"State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions","arxiv_id":"1910.00716","date":"2019-10-01","proceeding":null,"authors":["Kyu J. Han","Ramon Prieto","Kaixing Wu","Tao Ma"],"abstract":"Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown yet since it is challenging to handle highly correlated speech frames in the context of self-attention. In this paper we propose a new neural network model architecture, namely multi-stream self-attention, to address the issue thus make the self-attention mechanism more effective for speech recognition. The proposed model architecture consists of parallel streams of self-attention encoders, and each stream has layers of 1D convolutions with dilated kernels whose dilation rates are unique given stream, followed by a self-attention layer. The self-attention mechanism in each stream pays attention to only one resolution of input speech frames and the attentive computation can be more efficient. In a later stage, outputs from all the streams are concatenated then linearly projected to the final embedding. By stacking the proposed multi-stream self-attention encoder blocks and rescoring the resultant lattices with neural network language models, we achieve the word error rate of 2.2% on the test-clean dataset of the LibriSpeech corpus, the best number reported thus far on the dataset.","url_abs":"https://arxiv.org/abs/1910.00716v1","url_pdf":"https://arxiv.org/pdf/1910.00716v1.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":"state-of-the-art-speech-recognition-using","repo_url":"https://github.com/s-omranpour/Pytorch-Speech-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Multi-Stream Self-Attention With Dilated 1D Convolutions","rank_in_archive_order":32,"of":64,"metrics":{"Word Error Rate (WER)":"2.20"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Multi-Stream Self-Attention With Dilated 1D Convolutions","rank_in_archive_order":37,"of":53,"metrics":{"Word Error Rate (WER)":"5.80"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.00716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00716"}},"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/s-omranpour/Pytorch-Speech-Recognition","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"a63c5d31ea0ac430","entry":"get_same_pad","repo":"s-omranpour/Pytorch-Speech-Recognition","repo_kind":"listed","path":"src/modules.py","file_url":"https://github.com/s-omranpour/Pytorch-Speech-Recognition/blob/HEAD/src/modules.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a63c5d31ea0ac430"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}