For visual generation, discrete autoregressive models often struggle with poor tokenizer reconstruction, difficulties in sampling from large vocabularies, and slow token-by-token generation speeds. We ...

Abstract: The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence ...

Abstract: With the development of speech synthesis technology, the existing synthetic speech detection (SSD) methods cannot generalize well for unknown synthesis algorithms. And thus, this kind of ...