Time-Domain Multi-Modal Bone/Air Conducted Speech Enhancement

Adaptive Time Domain Signal Estimation for Multi-Microphone Speech Enhancement

In this paper, the main ideas of a new method for multi-microphone speech enhancement are presented. Combining previously known multichannel speech enhancement methods with Maximum A Posteriori (MAP) estimation concepts, and temporally whitenning the output noises, we obtain a new algorithm called Adaptive Time-domain Signal Estimation for MultiMicrophone (ATSEM). The simulations (using real-wo...

Speech enhancement using adaptive time-domain segmentation

In this paper, we investigate the benefits of using an adaptive segmentation of the speech signal in speech enhancement. The adaptive segmentation scheme divides the signal into the longest segments within which stationarity is preserved, thus providing a good time-frequency resolution. The segmentation is performed with the help of an orthogonal library of local cosine bases using a computatio...

Multi-Modal Hybrid Deep Neural Network for Speech Enhancement

Deep Neural Networks (DNN) have been successful in enhancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech signal. The quality of predicted features can be improved by providing additional side channel information that is robust to noise, such as visual cues. In this p...

Integrated speech enhancement and coding in the time-frequency domain

This paper addresses the problem of merging speech enhancement and coding in the context of an auditory modeling. The noisy signal is rst processed by a fast wavelet packet transform algorithm to obtain an auditory spectrum, from which a rough masking model is estimated. Then, this model is used to re ne a subtractive-type enhancement algorithm. The enhanced speech coe cients are then encoded i...

Silent-speech enhancement using body-conducted vocal-tract resonance signals