{"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/the-interpreter-understands-your-meaning-end","title":"The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation","arxiv_id":"2305.09652","date":"2023-05-16","proceeding":null,"authors":["Mutian He","Philip N. Garner"],"abstract":"End-to-end spoken language understanding (SLU) remains elusive even with current large pretrained language models on text and speech, especially in multilingual cases. Machine translation has been established as a powerful pretraining objective on text as it enables the model to capture high-level semantics of the input utterance and associations between different languages, which is desired for speech models that work on lower-level acoustic frames. Motivated particularly by the task of cross-lingual SLU, we demonstrate that the task of speech translation (ST) is a good means of pretraining speech models for end-to-end SLU on both intra- and cross-lingual scenarios. By introducing ST, our models reach higher performance over baselines on monolingual and multilingual intent classification as well as spoken question answering using SLURP, MINDS-14, and NMSQA benchmarks. To verify the effectiveness of our methods, we also create new benchmark datasets from both synthetic and real sources, for speech summarization and low-resource/zero-shot transfer from English to French or Spanish. We further show the value of preserving knowledge for the ST pretraining task for better downstream performance, possibly using Bayesian transfer regularizers.","url_abs":"https://arxiv.org/abs/2305.09652v2","url_pdf":"https://arxiv.org/pdf/2305.09652v2.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":"the-interpreter-understands-your-meaning-end","repo_url":"https://github.com/idiap/translation-aided-slu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"spoken-language-understanding","task_name":"Spoken Language Understanding"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"intent-classification-1","task_name":"intent-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.09652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09652"}},"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/idiap/translation-aided-slu","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"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":"a65d1cf4ea441a9a","entry":"build_asr_model","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/models/build.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":true,"mcp_get_code":{"code_sha256":"a65d1cf4ea441a9a"}},{"code_sha256_prefix":"25d5a7d5c1a1d739","entry":"build_classifier","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/models/build.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":true,"mcp_get_code":{"code_sha256":"25d5a7d5c1a1d739"}},{"code_sha256_prefix":"7fc2ab07411c3b47","entry":"build_text_decoder","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/models/build.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":true,"mcp_get_code":{"code_sha256":"7fc2ab07411c3b47"}},{"code_sha256_prefix":"6bc062e8e9560b15","entry":"get_audiofile","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/dataloader.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":true,"mcp_get_code":{"code_sha256":"6bc062e8e9560b15"}},{"code_sha256_prefix":"537bc17db309f75e","entry":"get_audiofile_spec","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"dataloader.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/dataloader.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":true,"mcp_get_code":{"code_sha256":"537bc17db309f75e"}},{"code_sha256_prefix":"a0ad3496d9b49bfc","entry":"is_weight_decayed","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/models/model.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":true,"mcp_get_code":{"code_sha256":"a0ad3496d9b49bfc"}},{"code_sha256_prefix":"2ae3cdbae25787c9","entry":"learning_rate_schedule","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/models/model.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":true,"mcp_get_code":{"code_sha256":"2ae3cdbae25787c9"}},{"code_sha256_prefix":"2d04e37fb39df9f3","entry":"normalize","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"corpora/covost2.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/corpora/covost2.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":true,"mcp_get_code":{"code_sha256":"2d04e37fb39df9f3"}},{"code_sha256_prefix":"068c70006f05aa82","entry":"normalize","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"corpora/gigawords.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/corpora/gigawords.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":true,"mcp_get_code":{"code_sha256":"068c70006f05aa82"}},{"code_sha256_prefix":"6d0ce37650057628","entry":"normalize","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"corpora/mustc.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/corpora/mustc.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":true,"mcp_get_code":{"code_sha256":"6d0ce37650057628"}},{"code_sha256_prefix":"8208905c59cd78a1","entry":"to_long_nonneg","repo":"idiap/translation-aided-slu","repo_kind":"official","path":"models/model.py","file_url":"https://github.com/idiap/translation-aided-slu/blob/HEAD/models/model.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":true,"mcp_get_code":{"code_sha256":"8208905c59cd78a1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}