{"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/learning-shared-semantic-space-for-speech-to","title":"Learning Shared Semantic Space for Speech-to-Text Translation","arxiv_id":"2105.03095","date":"2021-05-07","proceeding":"Findings (ACL) 2021 8","authors":["Chi Han","Mingxuan Wang","Heng Ji","Lei LI"],"abstract":"Having numerous potential applications and great impact, end-to-end speech translation (ST) has long been treated as an independent task, failing to fully draw strength from the rapid advances of its sibling - text machine translation (MT). With text and audio inputs represented differently, the modality gap has rendered MT data and its end-to-end models incompatible with their ST counterparts. In observation of this obstacle, we propose to bridge this representation gap with Chimera. By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art. Specifically, Chimera obtains 27.1 BLEU on MuST-C EN-DE, improving the SOTA by a +1.9 BLEU margin. Further experimental analyses demonstrate that the shared semantic space indeed conveys common knowledge between these two tasks and thus paves a new way for augmenting training resources across modalities. Code, data, and resources are available at https://github.com/Glaciohound/Chimera-ST.","url_abs":"https://arxiv.org/abs/2105.03095v3","url_pdf":"https://arxiv.org/pdf/2105.03095v3.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":"learning-shared-semantic-space-for-speech-to","repo_url":"https://github.com/Glaciohound/Chimera-SLT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-shared-semantic-space-for-speech-to","repo_url":"https://github.com/Glaciohound/Chimera-ST","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"speech-to-text","task_name":"Speech-to-Text"},{"task_slug":"speech-to-text-translation","task_name":"Speech-to-Text Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.03095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03095"}},"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/Glaciohound/Chimera-SLT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Glaciohound/Chimera-ST","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"b9a0bc0bcd225f48","entry":"HPathExists","repo":"Glaciohound/Chimera-SLT","repo_kind":"official","path":"fairseq/models/chimera/hdfs_utils.py","file_url":"https://github.com/Glaciohound/Chimera-SLT/blob/HEAD/fairseq/models/chimera/hdfs_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b9a0bc0bcd225f48"}},{"code_sha256_prefix":"2983c14177e64e70","entry":"RunCmd","repo":"Glaciohound/Chimera-SLT","repo_kind":"official","path":"fairseq/models/chimera/hdfs_utils.py","file_url":"https://github.com/Glaciohound/Chimera-SLT/blob/HEAD/fairseq/models/chimera/hdfs_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"2983c14177e64e70"}},{"code_sha256_prefix":"b78df00f83316feb","entry":"get_zip_manifest","repo":"Glaciohound/Chimera-SLT","repo_kind":"official","path":"chimera/prepare_data/data_utils.py","file_url":"https://github.com/Glaciohound/Chimera-SLT/blob/HEAD/chimera/prepare_data/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b78df00f83316feb"}},{"code_sha256_prefix":"04b7a7ee1905e73f","entry":"is_npy_data","repo":"Glaciohound/Chimera-SLT","repo_kind":"official","path":"chimera/prepare_data/data_utils.py","file_url":"https://github.com/Glaciohound/Chimera-SLT/blob/HEAD/chimera/prepare_data/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"04b7a7ee1905e73f"}},{"code_sha256_prefix":"9699b87654887b05","entry":"os_system","repo":"Glaciohound/Chimera-SLT","repo_kind":"official","path":"chimera/prepare_data/prep_mustc_data.py","file_url":"https://github.com/Glaciohound/Chimera-SLT/blob/HEAD/chimera/prepare_data/prep_mustc_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"9699b87654887b05"}},{"code_sha256_prefix":"5130a5ab54555aa3","entry":"search_gpu_script","repo":"Glaciohound/Chimera-SLT","repo_kind":"official","path":"chimera/generate/auto-generate.py","file_url":"https://github.com/Glaciohound/Chimera-SLT/blob/HEAD/chimera/generate/auto-generate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"5130a5ab54555aa3"}},{"code_sha256_prefix":"64a6b10b55526849","entry":"torchHLoad","repo":"Glaciohound/Chimera-SLT","repo_kind":"official","path":"fairseq/models/chimera/hdfs_utils.py","file_url":"https://github.com/Glaciohound/Chimera-SLT/blob/HEAD/fairseq/models/chimera/hdfs_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"64a6b10b55526849"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}