{"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/dailytalk-spoken-dialogue-dataset-for","title":"DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech","arxiv_id":"2207.01063","date":"2022-07-03","proceeding":null,"authors":["Keon Lee","Kyumin Park","Daeyoung Kim"],"abstract":"The majority of current Text-to-Speech (TTS) datasets, which are collections of individual utterances, contain few conversational aspects. In this paper, we introduce DailyTalk, a high-quality conversational speech dataset designed for conversational TTS. We sampled, modified, and recorded 2,541 dialogues from the open-domain dialogue dataset DailyDialog inheriting its annotated attributes. On top of our dataset, we extend prior work as our baseline, where a non-autoregressive TTS is conditioned on historical information in a dialogue. From the baseline experiment with both general and our novel metrics, we show that DailyTalk can be used as a general TTS dataset, and more than that, our baseline can represent contextual information from DailyTalk. The DailyTalk dataset and baseline code are freely available for academic use with CC-BY-SA 4.0 license.","url_abs":"https://arxiv.org/abs/2207.01063v3","url_pdf":"https://arxiv.org/pdf/2207.01063v3.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":"dailytalk-spoken-dialogue-dataset-for","repo_url":"https://github.com/keonlee9420/DailyTalk","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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":"dailytalk","name":"DailyTalk","full_name":"DailyTalk"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.01063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.01063"}},"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/keonlee9420/DailyTalk","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"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":1,"samples":[{"code_sha256_prefix":"2d5b4906f02da810","entry":"b_mas","repo":"keonlee9420/DailyTalk","repo_kind":"official","path":"model/modules.py","file_url":"https://github.com/keonlee9420/DailyTalk/blob/HEAD/model/modules.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d5b4906f02da810"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"keonlee9420/DailyTalk","repo_kind":"official","path":"hifigan/models.py","file_url":"https://github.com/keonlee9420/DailyTalk/blob/HEAD/hifigan/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"333927e3b7bdb68f","entry":"mas_width1","repo":"keonlee9420/DailyTalk","repo_kind":"official","path":"model/modules.py","file_url":"https://github.com/keonlee9420/DailyTalk/blob/HEAD/model/modules.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":"333927e3b7bdb68f"}},{"code_sha256_prefix":"2b5c06c1ba593c3c","entry":"read_lexicon","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2b5c06c1ba593c3c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}