Towards Universal Speech Discrete Tokens: A Case Study for ASR and TTS.
Yifan YangFeiyu ShenChenpeng DuZiyang MaKai YuDaniel PoveyXie ChenPublished in: ICASSP (2024)
Keyphrases
- text to speech
- automatic speech recognition
- speech recognition
- speech synthesis
- speech signal
- spontaneous speech
- sequence prediction
- word error rate
- speech corpus
- prosodic features
- noisy environments
- broadcast news
- case study
- test bed
- conversational speech
- text to speech synthesis
- hidden markov models
- spoken words
- speech retrieval
- vocal tract
- finite number
- error rate
- spoken document retrieval
- information retrieval
- endpoint detection
- pattern recognition
- speaker identification
- speech recognizers
- linear prediction
- language model
- image processing