Zero-Shot Code-Switching ASR and TTS with Multilingual Machine Speech Chain.
Sahoko NakayamaAndros TjandraSakriani SaktiSatoshi NakamuraPublished in: ASRU (2019)
Keyphrases
- text to speech
- automatic speech recognition
- speech recognition
- speech synthesis
- spontaneous speech
- speech signal
- prosodic features
- speech corpus
- word error rate
- multi lingual
- noisy environments
- conversational speech
- source code
- broadcast news
- digital libraries
- language model
- speech recognizers
- speech retrieval
- spoken words
- hidden markov models
- vocal tract
- speaker identification
- language independent
- flowshop
- language resources
- speaker recognition
- open source
- probabilistic model