Phonetic alignment: speech synthesis-based vs. Viterbi-based.
Fabrice MalfrèreOlivier DerooThierry DutoitChristophe RisPublished in: Speech Commun. (2003)
Keyphrases
- speech synthesis
- speech recognition
- hidden markov models
- vocal tract
- language model
- viterbi algorithm
- automatic speech recognition
- text to speech
- prosodic features
- speech signal
- word level
- dynamic time warping
- speaker identification
- image alignment
- noisy environments
- pattern recognition
- sequence alignment
- case study
- procrustes analysis
- speech corpus
- gesture recognition
- language independent
- markov model
- word alignment
- image processing
- information retrieval
- neural network
- database