Related papers: Neural Spatio-Temporal Beamformer for Target Speec…
Time-frequency masking or spectrum prediction computed via short symmetric windows are commonly used in low-latency deep neural network (DNN) based source separation. In this paper, we propose the usage of an asymmetric analysis-synthesis…
Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing…
Monaural Singing Voice Separation (MSVS) is a challenging task and has been studied for decades. Deep neural networks (DNNs) are the current state-of-the-art methods for MSVS. However, the existing DNNs are often designed manually, which is…
This paper describes our submission to the L3DAS22 Challenge Task 1, which consists of speech enhancement with 3D Ambisonic microphones. The core of our approach combines Deep Neural Network (DNN) driven complex spectral mapping with linear…
Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important issue associated with such approaches is that the intermediate…
Recently, stunning improvements on multi-channel speech separation have been achieved by neural beamformers when direction information is available. However, most of them neglect to utilize speaker's 2-dimensional (2D) location cues…
We propose Uni-ArrayDPS, a novel diffusion-based refinement framework for unified multi-channel speech enhancement and separation. Existing methods for multi-channel speech enhancement/separation are mostly discriminative and are highly…
Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both single-channel and multichannel conditions. However, severe performance degradation is still observed in the…
Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech by improving the intelligibility and naturalness. This is a challenging task especially for patients with severe dysarthria and speaking in…
In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the different spectro-temporal characteristics of the…
Modern smart glasses leverage advanced audio sensing and machine learning technologies to offer real-time transcribing and captioning services, considerably enriching human experiences in daily communications. However, such systems…
In the scenario with reverberation, the experience of human-machine interaction will become worse. In order to solve this problem, many methods for the dereverberation have emerged. At present, how to update the parameters of the Kalman…
In this paper, we address the problem of multichannel speech enhancement in the short-time Fourier transform (STFT) domain. A long short-time memory (LSTM) network takes as input a sequence of STFT coefficients associated with a frequency…
Conventional speech enhancement technique such as beamforming has known benefits for far-field speech recognition. Our own work in frequency-domain multi-channel acoustic modeling has shown additional improvements by training a spatial…
An important problem in ad-hoc microphone speech separation is how to guarantee the robustness of a system with respect to the locations and numbers of microphones. The former requires the system to be invariant to different indexing of the…
Recent research advances in deep neural network (DNN)-based beamformers have shown great promise for speech enhancement under adverse acoustic conditions. Different network architectures and input features have been explored in estimating…
The performance of speech enhancement algorithms in a multi-speaker scenario depends on correctly identifying the target speaker to be enhanced. Auditory attention decoding (AAD) methods allow to identify the target speaker which the…
Despite the rapid progress of automatic speech recognition (ASR) technologies targeting normal speech in recent decades, accurate recognition of dysarthric and elderly speech remains highly challenging tasks to date. Sources of…
Recent studies highlight the potential of textual modalities in conditioning the speech separation model's inference process. However, regularization-based methods remain underexplored despite their advantages of not requiring auxiliary…
The performance of speaker diarization is strongly affected by its clustering algorithm at the test stage. However, it is known that clustering algorithms are sensitive to random noises and small variations, particularly when the clustering…