Time Difference of Arrival Estimation of Speech Signals Using Deep Neural Networks with Integrated Time-frequency Masking.
Pasi PertiläMikko ParviainenPublished in: ICASSP (2019)
Keyphrases
- speech signal
- neural network
- speech recognition
- automatic speech recognition
- automatic speech recognition systems
- hidden markov models
- non stationary
- vocal tract
- additive noise
- signal processing
- pattern recognition
- frequency domain
- sound signals
- speech sounds
- linear prediction
- background noise
- speech enhancement
- blind source separation
- genetic algorithm
- noisy environments
- human visual system
- multi modal
- wavelet transform
- computer vision
- information retrieval