Speaker normalization on conversational telephone speech.
Steven WegmannDon McAllasterJeremy OrloffBarbara PeskinPublished in: ICASSP (1996)
Keyphrases
- speech recognition
- automatic speech recognition
- audio visual
- speaker recognition
- conversational speech
- speaker verification
- speaker identification
- multi modal
- spoken language
- automatic speech recognition systems
- prosodic features
- speaker diarization
- speaker dependent
- speech signal
- vocal tract
- speech synthesis
- speech sounds
- broadcast news
- conversational agent
- speaker adaptation
- acoustic features
- gaussian mixture model
- synthesized speech
- automatic transcription
- preprocessing
- audio stream
- hidden markov models
- endpoint detection
- human communication
- noisy environments
- normalization method
- speech recognizer
- call center
- probabilistic neural network
- phoneme recognition
- vector quantization
- feature vectors
- speaker independent
- language model
- text to speech
- digit recognition
- mel frequency cepstral coefficients
- visual information
- conversational agents
- multi stream
- natural language
- emotion recognition