Music removal by convolutional denoising autoencoder in speech recognition.
Mengyuan ZhaoDong WangZhiyong ZhangXuewei ZhangPublished in: APSIPA (2015)
Keyphrases
- speech recognition
- denoising
- restricted boltzmann machine
- image denoising
- language model
- hidden markov models
- speech synthesis
- noisy images
- deep learning
- speaker identification
- natural images
- automatic speech recognition
- audio signals
- pattern recognition
- speech recognizer
- speech signal
- speech processing
- image processing
- noise removal
- music information retrieval
- gaussian noise
- speech recognizers
- speech recognition technology
- keyword spotting
- speech recognition systems
- speaker independent
- noisy environments
- isolated word
- speech recognition errors
- cepstral coefficients
- speaker recognition
- conditional random fields
- multiscale