{"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/multichannel-av-wav2vec2-a-framework-for","title":"Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation","arxiv_id":"2401.03468","date":"2024-01-07","proceeding":null,"authors":["Qiushi Zhu","Jie Zhang","Yu Gu","Yuchen Hu","LiRong Dai"],"abstract":"Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the scarcity of labeled multichannel data and complex ambient noises. The efficacy of self-supervised learning for far-field multichannel and multi-modal speech processing has not been well explored. Considering that visual information helps to improve speech recognition performance in noisy scenes, in this work we propose a multichannel multi-modal speech self-supervised learning framework AV-wav2vec2, which utilizes video and multichannel audio data as inputs. First, we propose a multi-path structure to process multichannel audio streams and a visual stream in parallel, with intra- and inter-channel contrastive losses as training targets to fully exploit the spatiotemporal information in multichannel speech data. Second, based on contrastive learning, we use additional single-channel audio data, which is trained jointly to improve the performance of speech representation. Finally, we use a Chinese multichannel multi-modal dataset in real scenarios to validate the effectiveness of the proposed method on audio-visual speech recognition (AVSR), automatic speech recognition (ASR), visual speech recognition (VSR) and audio-visual speaker diarization (AVSD) tasks.","url_abs":"https://arxiv.org/abs/2401.03468v1","url_pdf":"https://arxiv.org/pdf/2401.03468v1.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":"multichannel-av-wav2vec2-a-framework-for","repo_url":"https://github.com/zqs01/multi-channel-wav2vec2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"audio-visual-speech-recognition","task_name":"Audio-Visual Speech Recognition"},{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speaker-diarization","task_name":"Speaker Diarization"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"visual-speech-recognition","task_name":"Visual Speech Recognition"},{"task_slug":"speaker-diarization","task_name":"speaker-diarization"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.03468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03468"}},"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/zqs01/multi-channel-wav2vec2","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/zqs01/multichannel-wav2vec2","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran_draft_wrong":3,"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":9,"samples":[{"code_sha256_prefix":"96cbb5e9ca5b6be0","entry":"Embedding","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avhubert/hubert_asr.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/hubert_asr.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"96cbb5e9ca5b6be0"}},{"code_sha256_prefix":"8cd8cb0d1e9e63e4","entry":"Linear","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avhubert/hubert_asr.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/hubert_asr.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8cd8cb0d1e9e63e4"}},{"code_sha256_prefix":"583f9780bdd00a45","entry":"conv3x3","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avhubert/resnet.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"583f9780bdd00a45"}},{"code_sha256_prefix":"d50e3a8f0b0f9a21","entry":"downsample_basic_block","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avhubert/resnet.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d50e3a8f0b0f9a21"}},{"code_sha256_prefix":"546a770034e200d1","entry":"downsample_basic_block_v2","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avhubert/resnet.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"546a770034e200d1"}},{"code_sha256_prefix":"ce7f0a006ef77ad3","entry":"label_len_fn","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avmc/avmc_finetuning.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avmc/avmc_finetuning.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ce7f0a006ef77ad3"}},{"code_sha256_prefix":"2c590c63adc5c7ef","entry":"load_audio_visual","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avhubert/hubert_dataset.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/hubert_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c590c63adc5c7ef"}},{"code_sha256_prefix":"113a523619225ba0","entry":"load_label","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avhubert/hubert_dataset.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/hubert_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"113a523619225ba0"}},{"code_sha256_prefix":"3e9450b6ac2fcddd","entry":"load_label_offset","repo":"zqs01/multi-channel-wav2vec2","repo_kind":"official","path":"avhubert/hubert_dataset.py","file_url":"https://github.com/zqs01/multi-channel-wav2vec2/blob/HEAD/avhubert/hubert_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e9450b6ac2fcddd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}