An i-vector Based Approach to Acoustic Sniffing for Irrelevant Variability Normalization Based Acoustic Model Training and Speech Recognition.
Jian XuYu ZhangZhi-Jie YanQiang HuoPublished in: INTERSPEECH (2011)
Keyphrases
- speech recognition
- acoustic models
- speech recognition systems
- speaker independent
- wall street journal corpus
- speech recognizers
- hidden markov models
- automatic speech recognition
- language model
- speech recognizer
- isolated word
- pattern recognition
- noisy speech
- speech processing
- speech synthesis
- speech signal
- speech understanding
- noisy environments
- speaker identification
- image processing
- discriminative training
- background noise
- keyword spotting
- acoustic features
- cepstral coefficients
- speech retrieval
- speech recognition technology
- mixture model
- training set
- feature vectors
- principal component analysis
- speech recognition errors
- machine learning