Unit Selection Speech Synthesis Using Frame-Sized Speech Segments and Neural Network Based Acoustic Models.
Zhen-Hua LingZhi-Ping ZhouPublished in: J. Signal Process. Syst. (2018)
Keyphrases
- speech synthesis
- speech recognition
- acoustic models
- automatic speech recognition
- speech segments
- speech retrieval
- speaker independent
- speech recognizer
- neural network
- text to speech
- hidden markov models
- speaker diarization
- pattern recognition
- language model
- speech signal
- broadcast news
- image processing
- video frames
- speaker identification
- feature vectors
- speech recognition systems
- computer vision
- feature extraction