Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition.
Krishna C. PuvvadaNithin Rao KoluguriKunal DhawanJagadeesh BalamBoris GinsburgPublished in: CoRR (2023)
Keyphrases
- speech recognition
- cepstral coefficients
- speaker identification
- speech signal
- speech processing
- speech recognition technology
- automatic speech recognition
- hidden markov models
- speaker dependent
- speech recognizer
- speech synthesis
- pattern recognition
- language model
- noisy environments
- speaker recognition
- gaussian mixture model
- speaker diarization
- mel frequency cepstral coefficients
- audio signal
- speech recognition systems
- computer vision
- signal processing
- speaker independent
- probabilistic neural network
- speech retrieval
- isolated word
- audio visual speech recognition
- acoustic features
- audio visual
- visual information
- feature extraction
- multimedia