{"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/can-we-use-common-voice-to-train-a-multi","title":"Can we use Common Voice to train a Multi-Speaker TTS system?","arxiv_id":"2210.06370","date":"2022-10-12","proceeding":null,"authors":["Sewade Ogun","Vincent Colotte","Emmanuel Vincent"],"abstract":"Training of multi-speaker text-to-speech (TTS) systems relies on curated datasets based on high-quality recordings or audiobooks. Such datasets often lack speaker diversity and are expensive to collect. As an alternative, recent studies have leveraged the availability of large, crowdsourced automatic speech recognition (ASR) datasets. A major problem with such datasets is the presence of noisy and/or distorted samples, which degrade TTS quality. In this paper, we propose to automatically select high-quality training samples using a non-intrusive mean opinion score (MOS) estimator, WV-MOS. We show the viability of this approach for training a multi-speaker GlowTTS model on the Common Voice English dataset. Our approach improves the overall quality of generated utterances by 1.26 MOS point with respect to training on all the samples and by 0.35 MOS point with respect to training on the LibriTTS dataset. This opens the door to automatic TTS dataset curation for a wider range of languages.","url_abs":"https://arxiv.org/abs/2210.06370v1","url_pdf":"https://arxiv.org/pdf/2210.06370v1.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":"can-we-use-common-voice-to-train-a-multi","repo_url":"https://github.com/ogunlao/glowtts_stdp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.06370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06370"}},"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/ogunlao/glowtts_stdp","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":9},"by_repo_kind":{"listed":{"samples":10,"ran":1,"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":"70a7614b3b3eb41f","entry":"unconstrained_rational_quadratic_spline","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"modules/glow_tts_modules/transforms.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/modules/glow_tts_modules/transforms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"70a7614b3b3eb41f"}},{"code_sha256_prefix":"63e4e54ac1c74e23","entry":"average_features","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"modules/glow_tts_with_pitch.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/modules/glow_tts_with_pitch.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":"63e4e54ac1c74e23"}},{"code_sha256_prefix":"7d5db48ab4981884","entry":"binarize_attention","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"utils/helpers.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/utils/helpers.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":"7d5db48ab4981884"}},{"code_sha256_prefix":"d2803ec5ec6424b4","entry":"convert_pad_shape","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"modules/glow_tts_modules/glow_tts_submodules.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/modules/glow_tts_modules/glow_tts_submodules.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":"d2803ec5ec6424b4"}},{"code_sha256_prefix":"698f219261aabb5e","entry":"get_batch_size","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"utils/helpers.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/utils/helpers.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":"698f219261aabb5e"}},{"code_sha256_prefix":"16f423dc8d011455","entry":"get_num_workers","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"utils/helpers.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/utils/helpers.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":"16f423dc8d011455"}},{"code_sha256_prefix":"f559e7146ee2b4ab","entry":"maximum_path","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"modules/glow_tts_modules/glow_tts_submodules.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/modules/glow_tts_modules/glow_tts_submodules.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":"f559e7146ee2b4ab"}},{"code_sha256_prefix":"ba6cafc4d658c14f","entry":"piecewise_rational_quadratic_transform","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"modules/glow_tts_modules/transforms.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/modules/glow_tts_modules/transforms.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":"ba6cafc4d658c14f"}},{"code_sha256_prefix":"e85d747983c4f5d8","entry":"searchsorted","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"modules/glow_tts_modules/transforms.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/modules/glow_tts_modules/transforms.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":"e85d747983c4f5d8"}},{"code_sha256_prefix":"a41c0f5898c9a01f","entry":"sequence_mask","repo":"ogunlao/glowtts_stdp","repo_kind":"listed","path":"modules/glow_tts_modules/glow_tts_submodules.py","file_url":"https://github.com/ogunlao/glowtts_stdp/blob/HEAD/modules/glow_tts_modules/glow_tts_submodules.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":"a41c0f5898c9a01f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}