Almost Unsupervised Text to Speech and Automatic Speech Recognition.
Yi RenXu TanTao QinSheng ZhaoZhou ZhaoTie-Yan LiuPublished in: ICML (2019)
Keyphrases
- automatic speech recognition
- text to speech
- speech recognition
- speech synthesis
- speech signal
- hidden markov models
- broadcast news
- speech corpus
- programming tool
- prosodic features
- word error rate
- spoken words
- speech retrieval
- conversational speech
- text to speech synthesis
- word recognition
- word processing
- noisy environments
- pattern recognition
- spontaneous speech
- recognition errors
- acoustic features
- speaker adaptation
- gesture recognition
- compound words
- language model
- multi modal
- speech sounds
- machine learning