{"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/utmos-utokyo-sarulab-system-for-voicemos","title":"UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022","arxiv_id":"2204.02152","date":"2022-04-05","proceeding":null,"authors":["Takaaki Saeki","Detai Xin","Wataru Nakata","Tomoki Koriyama","Shinnosuke Takamichi","Hiroshi Saruwatari"],"abstract":"We present the UTokyo-SaruLab mean opinion score (MOS) prediction system submitted to VoiceMOS Challenge 2022. The challenge is to predict the MOS values of speech samples collected from previous Blizzard Challenges and Voice Conversion Challenges for two tracks: a main track for in-domain prediction and an out-of-domain (OOD) track for which there is less labeled data from different listening tests. Our system is based on ensemble learning of strong and weak learners. Strong learners incorporate several improvements to the previous fine-tuning models of self-supervised learning (SSL) models, while weak learners use basic machine-learning methods to predict scores from SSL features. In the Challenge, our system had the highest score on several metrics for both the main and OOD tracks. In addition, we conducted ablation studies to investigate the effectiveness of our proposed methods.","url_abs":"https://arxiv.org/abs/2204.02152v2","url_pdf":"https://arxiv.org/pdf/2204.02152v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"utmos-utokyo-sarulab-system-for-voicemos","repo_url":"https://github.com/sarulab-speech/utmos22","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"utmos-utokyo-sarulab-system-for-voicemos","repo_url":"https://github.com/Edresson/ZS-TTS-Evaluation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"utmos-utokyo-sarulab-system-for-voicemos","repo_url":"https://github.com/takaaki-saeki/discretespeechmetrics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"utmos-utokyo-sarulab-system-for-voicemos","repo_url":"https://github.com/tarepan/speechmos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.02152","atlas_url":"https://app.syntology.ai/?focus=2204.02152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02152"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/takaaki-saeki/discretespeechmetrics","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Edresson/ZS-TTS-Evaluation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tarepan/speechmos","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sarulab-speech/utmos22","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":2,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":"f30ebf4e48b7e2d7","entry":"gelu","repo":"sarulab-speech/utmos22","repo_kind":"official","path":"strong/modules.py","file_url":"https://github.com/sarulab-speech/utmos22/blob/HEAD/strong/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"code_sha256_prefix":"fa7d5a0c8c69c41a","entry":"random_pitch_shift","repo":"sarulab-speech/utmos22","repo_kind":"official","path":"strong/data_augment.py","file_url":"https://github.com/sarulab-speech/utmos22/blob/HEAD/strong/data_augment.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":true,"mcp_get_code":{"code_sha256":"fa7d5a0c8c69c41a"}},{"code_sha256_prefix":"e0f5f157f0135f66","entry":"random_time_warp","repo":"sarulab-speech/utmos22","repo_kind":"official","path":"strong/data_augment.py","file_url":"https://github.com/sarulab-speech/utmos22/blob/HEAD/strong/data_augment.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":true,"mcp_get_code":{"code_sha256":"e0f5f157f0135f66"}},{"code_sha256_prefix":"d22a5e7495dd7a3a","entry":"compute_mask_indices","repo":"sarulab-speech/utmos22","repo_kind":"official","path":"strong/WavLM.py","file_url":"https://github.com/sarulab-speech/utmos22/blob/HEAD/strong/WavLM.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":true,"mcp_get_code":{"code_sha256":"d22a5e7495dd7a3a"}},{"code_sha256_prefix":"4aa7333ffd7e18c6","entry":"gelu_accurate","repo":"sarulab-speech/utmos22","repo_kind":"official","path":"strong/modules.py","file_url":"https://github.com/sarulab-speech/utmos22/blob/HEAD/strong/modules.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":true,"mcp_get_code":{"code_sha256":"4aa7333ffd7e18c6"}},{"code_sha256_prefix":"01233f4856456c5f","entry":"get_activation_fn","repo":"sarulab-speech/utmos22","repo_kind":"official","path":"strong/modules.py","file_url":"https://github.com/sarulab-speech/utmos22/blob/HEAD/strong/modules.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":true,"mcp_get_code":{"code_sha256":"01233f4856456c5f"}},{"code_sha256_prefix":"b6c0ff40845aeb01","entry":"train","repo":"sarulab-speech/utmos22","repo_kind":"official","path":"strong/param_tuning.py","file_url":"https://github.com/sarulab-speech/utmos22/blob/HEAD/strong/param_tuning.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":true,"mcp_get_code":{"code_sha256":"b6c0ff40845aeb01"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}