Speaker identification for whispered speech using modified temporal patterns and MFCCs.
Xing FanJohn H. L. HansenPublished in: INTERSPEECH (2009)
Keyphrases
- speaker identification
- temporal patterns
- speaker recognition
- speech recognition
- mel frequency cepstral coefficients
- speech signal
- gaussian mixture model
- audio features
- temporal information
- probabilistic neural network
- noisy environments
- broadcast news
- pattern discovery
- temporal constraints
- acoustic features
- hidden markov models
- language model
- automatic speech recognition
- feature extraction
- audio signal
- audio visual
- log files
- pattern recognition
- frequent patterns
- speaker verification
- feature set
- video search
- high dimensional
- em algorithm