{"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/towards-end-to-end-speech-recognition-with","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","arxiv_id":"1701.02720","date":"2017-01-10","proceeding":null,"authors":["Ying Zhang","Mohammad Pezeshki","Philemon Brakel","Saizheng Zhang","Cesar Laurent Yoshua Bengio","Aaron Courville"],"abstract":"Convolutional Neural Networks (CNNs) are effective models for reducing\nspectral variations and modeling spectral correlations in acoustic features for\nautomatic speech recognition (ASR). Hybrid speech recognition systems\nincorporating CNNs with Hidden Markov Models/Gaussian Mixture Models\n(HMMs/GMMs) have achieved the state-of-the-art in various benchmarks.\nMeanwhile, Connectionist Temporal Classification (CTC) with Recurrent Neural\nNetworks (RNNs), which is proposed for labeling unsegmented sequences, makes it\nfeasible to train an end-to-end speech recognition system instead of hybrid\nsettings. However, RNNs are computationally expensive and sometimes difficult\nto train. In this paper, inspired by the advantages of both CNNs and the CTC\napproach, we propose an end-to-end speech framework for sequence labeling, by\ncombining hierarchical CNNs with CTC directly without recurrent connections. By\nevaluating the approach on the TIMIT phoneme recognition task, we show that the\nproposed model is not only computationally efficient, but also competitive with\nthe existing baseline systems. Moreover, we argue that CNNs have the capability\nto model temporal correlations with appropriate context information.","url_abs":"http://arxiv.org/abs/1701.02720v1","url_pdf":"http://arxiv.org/pdf/1701.02720v1.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":"towards-end-to-end-speech-recognition-with","repo_url":"https://github.com/sdrobert/more-or-let","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"phoneme-recognition","task_name":"Phoneme Recognition"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.02720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.02720"}},"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/sdrobert/more-or-let","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"ran":0,"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":"af7e162a2d58f890","entry":"calculate_deltas","repo":"sdrobert/more-or-let","repo_kind":"listed","path":"pydrobert/mol/util.py","file_url":"https://github.com/sdrobert/more-or-let/blob/HEAD/pydrobert/mol/util.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":"af7e162a2d58f890"}},{"code_sha256_prefix":"fda094b2a766ba51","entry":"main","repo":"sdrobert/more-or-let","repo_kind":"listed","path":"stats.py","file_url":"https://github.com/sdrobert/more-or-let/blob/HEAD/stats.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":"fda094b2a766ba51"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}