Dataset Groups Activity Stream Hi-Fi Multi-Speaker English TTS dataset The Hi-Fi Multi-Speaker English TTS dataset is used to generate training, validation and test inputs for the audio splicing detection and localization task. BibTex: @dataset{Bakhturina_and_Lavrukhin_and_Ginsburg_and_Zhang_2024, abstract = {The Hi-Fi Multi-Speaker English TTS dataset is used to generate training, validation and test inputs for the audio splicing detection and localization task.}, author = {Bakhturina and Lavrukhin and Ginsburg and Zhang}, doi = {10.57702/pe0lntng}, institution = {No Organization}, keyword = {'multispeaker', 'speech synthesis', 'tts'}, month = {dec}, publisher = {TIB}, title = {Hi-Fi Multi-Speaker English TTS dataset}, url = {https://service.tib.eu/ldmservice/dataset/hi-fi-multi-speaker-english-tts-dataset}, year = {2024} }
