Unsupervised Features from Text for Speech Synthesis in a Speech-to-Speech Translation System.
Oliver WattsBowen ZhouPublished in: INTERSPEECH (2011)
Keyphrases
- speech synthesis
- text to speech
- speech recognition
- vocal tract
- prosodic features
- text to speech synthesis
- lexical features
- speech corpus
- speech recognition systems
- automatically extracted
- feature set
- speech signal
- hidden markov models
- information retrieval
- english text
- automatic speech recognition
- machine translation
- semantic information
- unsupervised learning
- content features
- text mining