{"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/speechformer-reducing-information-loss-in","title":"Speechformer: Reducing Information Loss in Direct Speech Translation","arxiv_id":"2109.04574","date":"2021-09-09","proceeding":"EMNLP 2021 11","authors":["Sara Papi","Marco Gaido","Matteo Negri","Marco Turchi"],"abstract":"Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer's quadratic complexity with respect to the input sequence length prevents its adoption as is with audio signals, which are typically represented by long sequences. Current solutions resort to an initial sub-optimal compression based on a fixed sampling of raw audio features. Therefore, potentially useful linguistic information is not accessible to higher-level layers in the architecture. To solve this issue, we propose Speechformer, an architecture that, thanks to reduced memory usage in the attention layers, avoids the initial lossy compression and aggregates information only at a higher level according to more informed linguistic criteria. Experiments on three language pairs (en->de/es/nl) show the efficacy of our solution, with gains of up to 0.8 BLEU on the standard MuST-C corpus and of up to 4.0 BLEU in a low resource scenario.","url_abs":"https://arxiv.org/abs/2109.04574v1","url_pdf":"https://arxiv.org/pdf/2109.04574v1.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":"speechformer-reducing-information-loss-in","repo_url":"https://github.com/sarapapi/fbk-fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speech-to-text-translation","task_name":"Speech-to-Text Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-to-text-translation-on-must-c-en-de","task":"Speech-to-Text Translation","dataset":"MuST-C EN->DE","model":"Speechformer","rank_in_archive_order":6,"of":8,"metrics":{"Case-sensitive sacreBLEU":"23.6"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-must-c-en-es","task":"Speech-to-Text Translation","dataset":"MuST-C EN->ES","model":"Speechformer","rank_in_archive_order":2,"of":5,"metrics":{"Case-sensitive sacreBLEU":"28.5"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-must-c-en-nl","task":"Speech-to-Text Translation","dataset":"MuST-C EN->NL","model":"Speechformer","rank_in_archive_order":1,"of":1,"metrics":{"Case-sensitive sacreBLEU":"27.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.04574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04574"}},"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/sarapapi/fbk-fairseq","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":4,"samples":[{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"sarapapi/fbk-fairseq","repo_kind":"official","path":"fairseq/binarizer.py","file_url":"https://github.com/sarapapi/fbk-fairseq/blob/HEAD/fairseq/binarizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"82bdf940665aeeb4"}},{"code_sha256_prefix":"9418b43048e4e4ec","entry":"url_to_filename","repo":"sarapapi/fbk-fairseq","repo_kind":"official","path":"fairseq/file_utils.py","file_url":"https://github.com/sarapapi/fbk-fairseq/blob/HEAD/fairseq/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"9418b43048e4e4ec"}},{"code_sha256_prefix":"aafdc12f01ab388f","entry":"filename_to_url","repo":"sarapapi/fbk-fairseq","repo_kind":"official","path":"fairseq/file_utils.py","file_url":"https://github.com/sarapapi/fbk-fairseq/blob/HEAD/fairseq/file_utils.py","link_basis":"harvester_set","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":"aafdc12f01ab388f"}},{"code_sha256_prefix":"0d372aa1e290a613","entry":"load_archive_file","repo":"sarapapi/fbk-fairseq","repo_kind":"official","path":"fairseq/file_utils.py","file_url":"https://github.com/sarapapi/fbk-fairseq/blob/HEAD/fairseq/file_utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d372aa1e290a613"}},{"code_sha256_prefix":"f7efe9d7d67792b5","entry":"new_groups","repo":"sarapapi/fbk-fairseq","repo_kind":"official","path":"fairseq/distributed_utils.py","file_url":"https://github.com/sarapapi/fbk-fairseq/blob/HEAD/fairseq/distributed_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":"f7efe9d7d67792b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}