Comparative Evaluations of Various Factored Deep Convolutional Rnn Architectures for Noise Robust Speech Recognition.
Masakiyo FujimotoHisashi KawaiPublished in: ICASSP (2018)
Keyphrases
- speech recognition
- noisy environments
- comparative evaluations
- speech signal
- hidden markov models
- automatic speech recognition
- speech understanding
- language model
- speaker identification
- background noise
- pattern recognition
- speech recognizer
- speech synthesis
- speech processing
- speech enhancement
- additive noise
- noisy speech
- speech recognition technology
- noise reduction
- digit recognition
- deep learning
- recurrent neural networks
- speech recognizers
- speech recognition systems
- acoustic models
- speaker dependent
- speech retrieval
- noise model
- machine learning
- isolated word
- speaker independent
- speaker diarization
- word recognition
- signal to noise ratio
- mobile devices
- information retrieval