Some Aspects of ASR Transcription Based Unsupervised Speaker Adaptation for HMM Speech Synthesis.
Bálint TóthTibor FegyóGéza NémethPublished in: TSD (2010)
Keyphrases
- speech recognition
- speech synthesis
- speaker adaptation
- automatic speech recognition
- speech recognition systems
- handwriting recognition
- speaker independent
- hidden markov models
- vocal tract
- speech signal
- speech recognizer
- speaker dependent
- prosodic features
- pattern recognition
- language model
- speech corpus
- speaker identification
- noisy environments
- unsupervised learning
- word recognition
- semi supervised
- broadcast news
- multi modal
- maximum likelihood
- machine learning