{"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/transformers-with-convolutional-context-for","title":"Transformers with convolutional context for ASR","arxiv_id":"1904.11660","date":"2019-04-26","proceeding":null,"authors":["Abdelrahman Mohamed","Dmytro Okhonko","Luke Zettlemoyer"],"abstract":"The recent success of transformer networks for neural machine translation and other NLP tasks has led to a surge in research work trying to apply it for speech recognition. Recent efforts studied key research questions around ways of combining positional embedding with speech features, and stability of optimization for large scale learning of transformer networks. In this paper, we propose replacing the sinusoidal positional embedding for transformers with convolutionally learned input representations. These contextual representations provide subsequent transformer blocks with relative positional information needed for discovering long-range relationships between local concepts. The proposed system has favorable optimization characteristics where our reported results are produced with fixed learning rate of 1.0 and no warmup steps. The proposed model achieves a competitive 4.7% and 12.9% WER on the Librispeech ``test clean'' and ``test other'' subsets when no extra LM text is provided.","url_abs":"https://arxiv.org/abs/1904.11660v2","url_pdf":"https://arxiv.org/pdf/1904.11660v2.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":"transformers-with-convolutional-context-for","repo_url":"https://github.com/George0828Zhang/simulst","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"transformers-with-convolutional-context-for","repo_url":"https://github.com/insop/pytorch-hackathon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"transformers-with-convolutional-context-for","repo_url":"https://github.com/sooftware/Fairseq-Listen-Attend-Spell","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"transformers-with-convolutional-context-for","repo_url":"https://github.com/sooftware/OpenSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.11660","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11660"}},"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/sooftware/Fairseq-Listen-Attend-Spell","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/George0828Zhang/simulst","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sooftware/OpenSpeech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/insop/pytorch-hackathon","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"listed":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"insop/pytorch-hackathon","repo_kind":"listed","path":"fairseq/fairseq/binarizer.py","file_url":"https://github.com/insop/pytorch-hackathon/blob/HEAD/fairseq/fairseq/binarizer.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":"82bdf940665aeeb4"}},{"code_sha256_prefix":"9d5ab7e22e729015","entry":"add_asr_eval_argument","repo":"insop/pytorch-hackathon","repo_kind":"listed","path":"asr-demo/infer_file.py","file_url":"https://github.com/insop/pytorch-hackathon/blob/HEAD/asr-demo/infer_file.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":"9d5ab7e22e729015"}},{"code_sha256_prefix":"6114b8f553b73b81","entry":"calc_mean_invstddev","repo":"insop/pytorch-hackathon","repo_kind":"listed","path":"asr-demo/infer_file.py","file_url":"https://github.com/insop/pytorch-hackathon/blob/HEAD/asr-demo/infer_file.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":"6114b8f553b73b81"}},{"code_sha256_prefix":"a0759a87ad6e2e61","entry":"compute_energy","repo":"insop/pytorch-hackathon","repo_kind":"listed","path":"asr-demo/vad.py","file_url":"https://github.com/insop/pytorch-hackathon/blob/HEAD/asr-demo/vad.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":"a0759a87ad6e2e61"}},{"code_sha256_prefix":"d07f4e99c3cd187c","entry":"compute_spectral_flatness","repo":"insop/pytorch-hackathon","repo_kind":"listed","path":"asr-demo/vad.py","file_url":"https://github.com/insop/pytorch-hackathon/blob/HEAD/asr-demo/vad.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":"d07f4e99c3cd187c"}},{"code_sha256_prefix":"9eda7f80331d658c","entry":"dataset_dest_prefix","repo":"insop/pytorch-hackathon","repo_kind":"listed","path":"fairseq/preprocess.py","file_url":"https://github.com/insop/pytorch-hackathon/blob/HEAD/fairseq/preprocess.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":"9eda7f80331d658c"}},{"code_sha256_prefix":"1045ab840c0cd71a","entry":"mono_to_color","repo":"insop/pytorch-hackathon","repo_kind":"listed","path":"asr-demo/utils.py","file_url":"https://github.com/insop/pytorch-hackathon/blob/HEAD/asr-demo/utils.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":"1045ab840c0cd71a"}},{"code_sha256_prefix":"15c34dd848773d02","entry":"process_predictions","repo":"insop/pytorch-hackathon","repo_kind":"listed","path":"asr-demo/infer_file.py","file_url":"https://github.com/insop/pytorch-hackathon/blob/HEAD/asr-demo/infer_file.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":"15c34dd848773d02"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}