Speech Pre-training with Acoustic Piece.
Shuo RenShujie LiuYu WuLong ZhouFuru WeiPublished in: CoRR (2022)
Keyphrases
- acoustic models
- speech recognition
- speech sounds
- hearing impaired
- speech recognition systems
- training set
- emotional speech
- speech signal
- acoustic features
- hidden markov models
- training phase
- prosodic features
- emotion recognition
- automatic speech recognition
- acoustic signal
- training algorithm
- training examples
- broadcast news
- text to speech
- discriminative training
- speech synthesis
- speech recognizer
- training process