An i-vector Based Approach to Training Data Clustering for Improved Speech Recognition.
Yu ZhangJian XuZhi-Jie YanQiang HuoPublished in: INTERSPEECH (2011)
Keyphrases
- speech recognition
- data clustering
- wall street journal corpus
- isolated word
- clustering algorithm
- unsupervised learning
- acoustic models
- hidden markov models
- language model
- automatic speech recognition
- k means
- speech synthesis
- cluster analysis
- speech recognizer
- speech signal
- speech recognition technology
- supervised learning
- pattern recognition
- speech processing
- speaker identification
- training set
- speech recognition systems
- training process
- speech retrieval
- neural network
- speech recognizers
- high dimensional
- data mining