{"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/using-speech-synthesis-to-train-end-to-end","title":"Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models","arxiv_id":"1910.09463","date":"2019-10-21","proceeding":null,"authors":["Loren Lugosch","Brett Meyer","Derek Nowrouzezahrai","Mirco Ravanelli"],"abstract":"End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained speech recognizer and natural language understanding module. The downside of end-to-end SLU is that in-domain speech data must be recorded to train the model. In this paper, we propose a strategy for overcoming this requirement in which speech synthesis is used to generate a large synthetic training dataset from several artificial speakers. Experiments on two open-source SLU datasets confirm the effectiveness of our approach, both as a sole source of training data and as a form of data augmentation.","url_abs":"https://arxiv.org/abs/1910.09463v1","url_pdf":"https://arxiv.org/pdf/1910.09463v1.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":"using-speech-synthesis-to-train-end-to-end","repo_url":"https://github.com/lorenlugosch/end-to-end-SLU","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"using-speech-synthesis-to-train-end-to-end","repo_url":"https://github.com/dscripka/openwakeword","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"using-speech-synthesis-to-train-end-to-end","repo_url":"https://github.com/lorenlugosch/pretrain_speech_model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"spoken-language-understanding","task_name":"Spoken Language Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/spoken-language-understanding-on-snips","task":"Spoken Language Understanding","dataset":"Snips-SmartLights","model":"Real + synthetic","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy (%)":"71.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.09463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09463"}},"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/lorenlugosch/pretrain_speech_model","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dscripka/openwakeword","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lorenlugosch/end-to-end-SLU","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":11},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"listed":{"samples":8,"ran":1,"repositories":2}},"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":"b380f42b5b71cc47","entry":"flip","repo":"lorenlugosch/pretrain_speech_model","repo_kind":"listed","path":"models.py","file_url":"https://github.com/lorenlugosch/pretrain_speech_model/blob/HEAD/models.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b380f42b5b71cc47"}},{"code_sha256_prefix":"9db28a334416e5df","entry":"flatten_features","repo":"dscripka/openwakeword","repo_kind":"listed","path":"openwakeword/custom_verifier_model.py","file_url":"https://github.com/dscripka/openwakeword/blob/HEAD/openwakeword/custom_verifier_model.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":"9db28a334416e5df"}},{"code_sha256_prefix":"dabffaf05575f6d7","entry":"generate_roc_curve_fprs","repo":"dscripka/openwakeword","repo_kind":"listed","path":"openwakeword/metrics.py","file_url":"https://github.com/dscripka/openwakeword/blob/HEAD/openwakeword/metrics.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":"dabffaf05575f6d7"}},{"code_sha256_prefix":"33313e78c0675262","entry":"generate_roc_curve_tprs","repo":"dscripka/openwakeword","repo_kind":"listed","path":"openwakeword/metrics.py","file_url":"https://github.com/dscripka/openwakeword/blob/HEAD/openwakeword/metrics.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":"33313e78c0675262"}},{"code_sha256_prefix":"65bb5581084bcf53","entry":"get_false_positives","repo":"dscripka/openwakeword","repo_kind":"listed","path":"openwakeword/metrics.py","file_url":"https://github.com/dscripka/openwakeword/blob/HEAD/openwakeword/metrics.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":"65bb5581084bcf53"}},{"code_sha256_prefix":"29a834b140b9fee7","entry":"has_params","repo":"lorenlugosch/end-to-end-SLU","repo_kind":"official","path":"models.py","file_url":"https://github.com/lorenlugosch/end-to-end-SLU/blob/HEAD/models.py","link_basis":"first_harvest_node","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":"29a834b140b9fee7"}},{"code_sha256_prefix":"bccf5e2ef3b3fc2c","entry":"re_arg","repo":"dscripka/openwakeword","repo_kind":"listed","path":"openwakeword/utils.py","file_url":"https://github.com/dscripka/openwakeword/blob/HEAD/openwakeword/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":"bccf5e2ef3b3fc2c"}},{"code_sha256_prefix":"3a8129d8532e445f","entry":"read_config","repo":"lorenlugosch/end-to-end-SLU","repo_kind":"official","path":"data.py","file_url":"https://github.com/lorenlugosch/end-to-end-SLU/blob/HEAD/data.py","link_basis":"first_harvest_node","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":"3a8129d8532e445f"}},{"code_sha256_prefix":"fdfd505e22326547","entry":"rms_energy","repo":"lorenlugosch/end-to-end-SLU","repo_kind":"official","path":"data.py","file_url":"https://github.com/lorenlugosch/end-to-end-SLU/blob/HEAD/data.py","link_basis":"first_harvest_node","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":"fdfd505e22326547"}},{"code_sha256_prefix":"be70acdc3215c288","entry":"sinc","repo":"lorenlugosch/end-to-end-SLU","repo_kind":"official","path":"models.py","file_url":"https://github.com/lorenlugosch/end-to-end-SLU/blob/HEAD/models.py","link_basis":"first_harvest_node","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":"be70acdc3215c288"}},{"code_sha256_prefix":"2d07a7c28d9ef33e","entry":"stack_clips","repo":"dscripka/openwakeword","repo_kind":"listed","path":"openwakeword/data.py","file_url":"https://github.com/dscripka/openwakeword/blob/HEAD/openwakeword/data.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":"2d07a7c28d9ef33e"}},{"code_sha256_prefix":"09b738a34151425e","entry":"train_verifier_model","repo":"dscripka/openwakeword","repo_kind":"listed","path":"openwakeword/custom_verifier_model.py","file_url":"https://github.com/dscripka/openwakeword/blob/HEAD/openwakeword/custom_verifier_model.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":"09b738a34151425e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}