Distant-talking speaker identification by generalized spectral subtraction-based dereverberation and its efficient computation.
Zhaofeng ZhangLongbiao WangAtsuhiko KaiPublished in: EURASIP J. Audio Speech Music. Process. (2014)
Keyphrases
- efficient computation
- speaker identification
- speech signal
- speech recognition
- noisy environments
- automatic speech recognition
- gaussian mixture model
- computational efficiency
- feature extraction
- non stationary
- hidden markov models
- broadcast news
- support vector machine
- language model
- mixture model
- data sets
- pattern recognition
- support vector
- training data
- similarity measure
- high level