Attention-Based Joint Training of Noise Suppression and Sound Event Detection for Noise-Robust Classification

Luminance degradation compensation based on multi stream self attention to address thin film transistor organic light emitting diode burn in

Robust localization employing weighted least squares method based on MM estimator and Kalman Filter with maximum versoria criterion

Novel data augmentation employing multivariate Gaussian distribution for neural network based blood pressure estimation

Deep Q-network-based noise suppression for robust speech recognition

Exploiting deep neural networks for two-to-five channel surround decoder

Document-Level Neural TTS Using Curriculum Learning and Attention Masking

Multi-TALK: Multi-Microphone Cross-Tower Network for Jointly Suppressing Acoustic Echo and Background Noise

Delayless Block Individual-Weighting-Factors Sign Subband Adaptive Filters With an Improved Band-Dependent Variable Step-Size

End-to-End Speech Endpoint Detection Utilizing Acoustic and Language Modeling Knowledge for Online Low-Latency Speech Recognition