3 accepted papers
Autoregressive (AR) frameworks have recently achieved remarkable progress in zero-shot text-to-speech (TTS) by leveraging discrete speech tokens and large language model techniques. Despite their success, existing AR-based zero-shot TTS systems face two critical limitations: (i) an inherent speed-qu…
Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for a comprehensive understanding of human communication, as NV…
Studies of speech representation enhance zero-shot Text-to-Speech by mapping text to intermediate representations before generating speech. However, using representations often struggles to balance linguistic, para-linguistic, and non-linguistic information in speech during the synthesis phase. Addi…