Towards an Intelligent Acoustic Front End for Automatic Speech Recognition: Built-in Speaker Normalization.
Umit H. YapanelJohn H. L. HansenPublished in: EURASIP J. Audio Speech Music. Process. (2008)
Keyphrases
- automatic speech recognition
- acoustic features
- speech sounds
- speech recognition
- speech recognizers
- acoustic models
- speech segments
- hidden markov models
- speech signal
- word error rate
- speech recognition systems
- broadcast news
- formant frequencies
- speaker independent
- conversational speech
- spontaneous speech
- spoken words
- mel frequency cepstral coefficients
- speech corpus
- speaker dependent
- noisy environments
- speaker adaptation
- pattern recognition
- speech recognizer
- word recognition
- recognition errors
- language model
- phoneme recognition
- music information retrieval
- information retrieval
- speaker verification
- machine learning