Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition.
Krishna C. PuvvadaNithin Rao KoluguriKunal DhawanJagadeesh BalamBoris GinsburgPublished in: ICASSP (2024)
Keyphrases
- speech recognition
- cepstral coefficients
- speaker identification
- speech signal
- speech processing
- automatic speech recognition
- speech recognition technology
- hidden markov models
- language model
- pattern recognition
- speech recognizer
- speech synthesis
- mel frequency cepstral coefficients
- speaker recognition
- noisy environments
- speaker dependent
- speech recognizers
- speech recognition systems
- audio visual speech recognition
- speaker diarization
- speaker adaptation
- audio visual
- broadcast news
- gaussian mixture model
- speaker independent
- signal processing
- speech retrieval
- audio signals
- vocal tract
- multi stream
- acoustic features
- feature selection
- word recognition
- probabilistic model
- multimedia
- image processing