pMCT: Patched Multi-Condition Training for Robust Speech Recognition.
Pablo Peso ParadaAgnieszka DobrowolskaKarthikeyan SaravananMete OzayPublished in: INTERSPEECH (2022)
Keyphrases
- speech recognition
- noisy environments
- wall street journal corpus
- hidden markov models
- isolated word
- speech processing
- speech recognizer
- speech signal
- language model
- speech synthesis
- automatic speech recognition
- acoustic models
- speaker identification
- pattern recognition
- speech understanding
- speech recognition technology
- neural network
- speech recognizers
- keyword spotting
- speech retrieval
- speaker independent
- cepstral coefficients
- image processing
- machine learning
- speaker dependent
- speech recognition systems
- training process
- speaker diarization