Related papers: Harmonic enhancement using learnable comb filter f…
Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution. In this paper, a light-weight full-band model is proposed with two dedicated…
It is highly desirable that speech enhancement algorithms can achieve good performance while keeping low latency for many applications, such as digital hearing aids, acoustically transparent hearing devices, and public address systems. To…
Complex-valued processing has brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram, while complex masks…
The direct expansion of deep neural network (DNN) based wide-band speech enhancement (SE) to full-band processing faces the challenge of low frequency resolution in low frequency range, which would highly likely lead to deteriorated…
For the difficulty and large computational complexity of modeling more frequency bands, full-band speech enhancement based on deep neural networks is still challenging. Previous studies usually adopt compressed full-band speech features in…
Due to the high computational complexity to model more frequency bands, it is still intractable to conduct real-time full-band speech enhancement based on deep neural networks. Recent studies typically utilize the compressed perceptually…
Over the past few years, speech enhancement methods based on deep learning have greatly surpassed traditional methods based on spectral subtraction and spectral estimation. Many of these new techniques operate directly in the the short-time…
This paper proposes a model that integrates sub-band processing and deep filtering to fully exploit information from the target time-frequency (TF) bin and its surrounding TF bins for single-channel speech enhancement. The sub-band module…
Multi-channel speech enhancement with ad-hoc sensors has been a challenging task. Speech model guided beamforming algorithms are able to recover natural sounding speech, but the speech models tend to be oversimplified or the inference would…
The quality of speech codecs deteriorates at low bitrates due to high quantization noise. A post-filter is generally employed to enhance the quality of the coded speech. In this paper, a data-driven post-filter relying on masking in the…
Optical frequency combs can potentially provide an efficient light source for multi-terabit-per-second optical superchannels. However, as the bandwidth of these multi-wavelength light sources is increased, it can result in low per-line…
Despite noise suppression being a mature area in signal processing, it remains highly dependent on fine tuning of estimator algorithms and parameters. In this paper, we demonstrate a hybrid DSP/deep learning approach to noise suppression. A…
Classical speech coding uses low-complexity postfilters with zero lookahead to enhance the quality of coded speech, but their effectiveness is limited by their simplicity. Deep Neural Networks (DNNs) can be much more effective, but require…
Deep learning-based speech enhancement has seen huge improvements and recently also expanded to full band audio (48 kHz). However, many approaches have a rather high computational complexity and require big temporal buffers for real time…
The performance of deep learning-based multi-channel speech enhancement methods often deteriorates when the geometric parameters of the microphone array change. Traditional approaches to mitigate this issue typically involve training on…
Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement.…
Mel-scale spectrum features are used in various recognition and classification tasks on speech signals. There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV). This paper…
A novel tool, based on Bayesian filtering framework and expectation maximization algorithm, is numerically and experimentally demonstrated for accurate frequency comb noise characterization. The tool is statistically optimum in a…
Single-channel speech enhancement with deep neural networks (DNNs) has shown promising performance and is thus intensively being studied. In this paper, instead of applying the mean squared error (MSE) as the loss function during DNN…
We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…