Speech Data Clustering Based on Phoneme Error Trend for Unsupervised Acoustic Model Adaptation.
Taichi AsamiSatoshi KobashikawaHirokazu MasatakiOsamu YoshiokaSatoshi TakahashiPublished in: INTERSPEECH (2012)
Keyphrases
- data sets
- data structure
- synthetic data
- raw data
- data analysis
- hidden markov models
- end users
- knowledge discovery
- data processing
- input data
- data quality
- speech recognition
- statistical analysis
- database
- data points
- high quality
- training data
- semi supervised
- data collection
- unsupervised learning
- labeled data
- error rate
- pattern recognition
- spatial data
- data mining
- spoken language
- speech synthesis