Testing the consistency assumption: Pronunciation variant forced alignment in read and spontaneous speech synthesis.
Rasmus DallSandrine BrognauxKorin RichmondCassia Valentini-BotinhaoGustav Eje HenterJulia HirschbergJunichi YamagishiSimon KingPublished in: ICASSP (2016)
Keyphrases
- speech synthesis
- speech recognition
- language model
- vocal tract
- prosodic features
- hidden markov models
- automatic speech recognition
- pattern recognition
- text to speech
- speech signal
- speech corpus
- image alignment
- speaker identification
- conversational speech
- noisy environments
- dynamic time warping
- language learning
- neural network