Two-Step Joint Optimization with Auxiliary Loss Function for Noise-Robust Speech Recognition.
Geon Woo LeeHong Kook KimPublished in: Sensors (2022)
Keyphrases
- speech recognition
- loss function
- joint optimization
- noisy environments
- hidden markov models
- pairwise
- automatic speech recognition
- speech synthesis
- speaker identification
- speech signal
- noisy speech
- language model
- speech processing
- support vector
- speech recognizer
- background noise
- speech recognition systems
- speech recognition technology
- pattern recognition
- noise reduction
- speaker independent
- speaker dependent
- noise model
- sparse representation
- knn
- convex loss functions