{"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/ttsds-text-to-speech-distribution-score","title":"TTSDS -- Text-to-Speech Distribution Score","arxiv_id":"2407.12707","date":"2024-07-17","proceeding":null,"authors":["Christoph Minixhofer","Ondřej Klejch","Peter Bell"],"abstract":"Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose evaluating the quality of synthetic speech as a combination of multiple factors such as prosody, speaker identity, and intelligibility. Our approach assesses how well synthetic speech mirrors real speech by obtaining correlates of each factor and measuring their distance from both real speech datasets and noise datasets. We benchmark 35 TTS systems developed between 2008 and 2024 and show that our score computed as an unweighted average of factors strongly correlates with the human evaluations from each time period.","url_abs":"https://arxiv.org/abs/2407.12707v3","url_pdf":"https://arxiv.org/pdf/2407.12707v3.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":"ttsds-text-to-speech-distribution-score","repo_url":"https://github.com/ttsds/ttsds","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[{"slug":"ttsds-synthetic-speech","name":"TTSDS Synthetic Speech","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.12707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12707"}},"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/ttsds/ttsds","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"3ec3eb20d7afda64","entry":"frechet_distance","repo":"ttsds/ttsds","repo_kind":"official","path":"src/ttsds/util/distances.py","file_url":"https://github.com/ttsds/ttsds/blob/HEAD/src/ttsds/util/distances.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3ec3eb20d7afda64"}},{"code_sha256_prefix":"0e46302ef1b09ae6","entry":"frechet_distance_fast","repo":"ttsds/ttsds","repo_kind":"official","path":"src/ttsds/util/distances.py","file_url":"https://github.com/ttsds/ttsds/blob/HEAD/src/ttsds/util/distances.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e46302ef1b09ae6"}},{"code_sha256_prefix":"15acedbab8c34949","entry":"hash_md5","repo":"ttsds/ttsds","repo_kind":"official","path":"src/ttsds/util/cache.py","file_url":"https://github.com/ttsds/ttsds/blob/HEAD/src/ttsds/util/cache.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"15acedbab8c34949"}},{"code_sha256_prefix":"a28e9220c31fb21d","entry":"wada_snr","repo":"ttsds/ttsds","repo_kind":"official","path":"src/ttsds/benchmarks/environment/wada_snr.py","file_url":"https://github.com/ttsds/ttsds/blob/HEAD/src/ttsds/benchmarks/environment/wada_snr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a28e9220c31fb21d"}},{"code_sha256_prefix":"54f57814da820cb0","entry":"wasserstein_distance","repo":"ttsds/ttsds","repo_kind":"official","path":"src/ttsds/util/distances.py","file_url":"https://github.com/ttsds/ttsds/blob/HEAD/src/ttsds/util/distances.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"54f57814da820cb0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}