Towards an Intelligent Acoustic Front-End for Automatic Speech Recognition: Built-In Speaker Normalization (BISN).
Umit H. YapanelJohn H. L. HansenPublished in: ICASSP (1) (2005)
Keyphrases
- automatic speech recognition
- acoustic features
- speech sounds
- speech recognition
- speech recognizers
- acoustic models
- speech segments
- speech signal
- word error rate
- hidden markov models
- conversational speech
- broadcast news
- speech recognition systems
- speaker independent
- spoken words
- speech retrieval
- noisy environments
- language model
- speech synthesis
- recognition errors
- formant frequencies
- spontaneous speech
- word recognition
- discriminative training
- speaker verification
- prosodic features
- speaker adaptation
- speech recognizer
- speech corpus
- speaker dependent
- speaker recognition
- speaker identification
- sound source
- linear prediction
- visual features
- information retrieval systems