Compressing Speech Recognition Networks with MLP via Tensor-Train Decomposition.
Dan HeYubin ZhongPublished in: APSIPA (2019)
Keyphrases
- speech recognition
- hidden markov models
- language model
- automatic speech recognition
- speech signal
- speech synthesis
- neural network
- speech processing
- speech understanding
- multilayer perceptron
- speech recognizer
- speech recognition systems
- pattern recognition
- noisy environments
- speaker identification
- speech recognizers
- keyword spotting
- speech recognition technology
- artificial neural networks
- speaker dependent
- image processing
- speech recognition errors
- isolated word
- speaker independent
- back propagation
- cepstral coefficients
- n gram
- feature space
- information retrieval
- machine learning