Code-Switching ASR and TTS Using Semisupervised Learning with Machine Speech Chain.
Sahoko NakayamaAndros TjandraSakriani SaktiSatoshi NakamuraPublished in: IEICE Trans. Inf. Syst. (2021)
Keyphrases
- semisupervised learning
- text to speech
- automatic speech recognition
- speech recognition
- speech synthesis
- spontaneous speech
- prosodic features
- speech signal
- semi supervised learning
- speech corpus
- cost sensitive
- computational linguistics
- broadcast news
- word error rate
- noisy environments
- co training
- supervised learning
- supervised and unsupervised learning
- word processing
- unlabeled data
- data sets
- hidden markov models
- human machine interaction
- semi supervised
- text classification
- language model
- pattern recognition
- probabilistic model
- multi class
- labeled data
- training set
- feature space
- dimensionality reduction
- feature extraction
- natural language processing