DNN-based enhancement of noisy and reverberant speech.
Yan ZhaoDeLiang WangIvo MerksTao ZhangPublished in: ICASSP (2016)
Keyphrases
- speech signal
- noisy environments
- speech recognition
- automatic speech recognition
- speaker identification
- vocal tract
- linear prediction
- automatic speech recognition systems
- speech quality
- image enhancement
- speaker verification
- image processing
- noisy data
- non stationary
- training process
- hidden markov models
- data sets
- speech processing
- computer vision
- spoken language
- speaker recognition
- noise free
- speech synthesis
- neural network
- image sequences
- endpoint detection
- text to speech synthesis
- pattern recognition