{"doi":"10.21437/interspeech.2021-341","title":"RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis","abstract":"This paper introduces RyanSpeech, a new speech corpus for research on automated text-to-speech (TTS) systems. Publicly available TTS corpora are often noisy, recorded with multiple speakers, or lack quality male speech data. In order to meet the need for a high quality, publicly available male speech corpus within the field of speech recognition, we have designed and created RyanSpeech which contains textual materials from real-world conversational settings. These materials contain over 10 hours of a professional male voice actor's speech recorded at 44.1 kHz. This corpus's design and pipeline make RyanSpeech ideal for developing TTS systems in real-world applications. To provide a baseline for future research, protocols, and benchmarks, we trained 4 state-of-the-art speech models and a vocoder on RyanSpeech. The results show 3.36 in mean opinion scores (MOS) in our best model. We have made both the corpus and trained models for public use.","journal":"arXiv (Cornell University)","year":2021,"id":220972,"datarank":0.1143746173009853,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"self_citation_contribution":0.10397207708399181,"citation_network_contribution":0.010402540216993493,"self_endowment_contribution":0.10397207708399181,"citer_contribution":0.010402540216993493,"corpus_percentile":28.12717567881179,"corpus_rank":9292,"citation_count":1,"citer_count":1,"citers_with_citation_signal":1,"citers_with_endowment":1,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.9223,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":820687,"name":"Mohammad H. Mahoor","orcid":"0000-0001-8923-4660","position":1,"is_corresponding":false},{"id":821062,"name":"Julia Madsen","orcid":null,"position":2,"is_corresponding":false},{"id":821063,"name":"Eshrat S. Emamian","orcid":null,"position":3,"is_corresponding":false},{"id":821061,"name":"Rohola Zandie","orcid":null,"position":0,"is_corresponding":true}],"reference_count":19,"raw_metadata":null,"created_at":"2026-07-18T23:53:50.838581Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}