Noisy training for deep neural networks in speech recognition.
Shi YinChao LiuZhiyong ZhangYiye LinDong WangJavier TejedorThomas Fang ZhengYinguo LiPublished in: EURASIP J. Audio Speech Music. Process. (2015)
Keyphrases
- speech recognition
- neural network
- noisy environments
- pattern recognition
- wall street journal corpus
- training process
- isolated word
- hidden markov models
- acoustic models
- language model
- speech recognizer
- speech signal
- speech understanding
- automatic speech recognition
- speech processing
- speech synthesis
- speech recognizers
- speech recognition systems
- speech recognition technology
- speech recognition errors
- keyword spotting
- training set
- speaker identification
- deep learning
- speaker independent
- back propagation
- speaker diarization
- background noise
- speech retrieval
- handwriting recognition
- feature vectors