A Deep Neural Network Approach for Missing-Data Mask Estimation on Dual-Microphone Smartphones: Application to Noise-Robust Speech Recognition.
Iván López-EspejoJosé A. GonzálezÁngel M. GómezAntonio M. PeinadoPublished in: IberSPEECH (2014)
Keyphrases
- missing data
- speech recognition
- noisy environments
- automatic speech recognition
- neural network
- pattern recognition
- missing values
- incomplete data
- structure from motion
- low rank
- hidden markov models
- language model
- speech signal
- speech recognizer
- speech processing
- speech synthesis
- imprecise data
- speaker diarization
- speech recognition technology
- speaker identification
- background noise
- audio visual speech recognition
- multiple imputation
- dimensionality reduction
- image processing