Cross-Utterance Conditioned VAE for Speech Generation.
Yang LiCheng YuGuangzhi SunWeiqin ZuZheng TianYing WenWei PanChao ZhangJun WangYang YangFanglei SunPublished in: CoRR (2023)
Keyphrases
- speech recognition
- spoken language
- speech recognizer
- automatic speech recognition
- speech synthesis
- language model
- speech signal
- hidden markov models
- audio visual
- generation process
- speaker identification
- text to speech
- endpoint detection
- real time
- conversational speech
- recognition engine
- broadcast news
- linear prediction
- noisy environments
- dialogue system
- pattern recognition
- information systems
- data sets