Joint Adversarial Training of Speech Recognition and Synthesis Models for Many-to-One Voice Conversion Using Phonetic Posteriorgrams.
Yuki SaitoKei AkuzawaKentaro TachibanaPublished in: IEICE Trans. Inf. Syst. (2020)
Keyphrases
- speech recognition
- acoustic models
- speech recognizer
- speech synthesis
- isolated word
- hidden markov models
- speaker independent
- speech processing
- wall street journal corpus
- speech understanding
- automatic speech recognition
- speaker identification
- language model
- speech recognition errors
- pattern recognition
- noisy environments
- speech recognition technology
- broadcast news
- spoken language
- keyword spotting
- speech signal
- speech recognizers
- training data