Related papers: BS-PLCNet: Band-split Packet Loss Concealment Netw…
The goal of this work is to develop a meeting transcription system that can recognize speech even when utterances of different speakers are overlapped. While speech overlaps have been regarded as a major obstacle in accurately transcribing…
Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several…
Despite the remarkable success of pre-trained language models (PLMs), they still face two challenges: First, large-scale PLMs are inefficient in terms of memory footprint and computation. Second, on the downstream tasks, PLMs tend to rely…
Deep complex convolution recurrent network (DCCRN), which extends CRN with complex structure, has achieved superior performance in MOS evaluation in Interspeech 2020 deep noise suppression challenge (DNS2020). This paper further extends…
Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an audiovisual (AV) system for speech enhancement, target speaker extraction, and multi-talker speaker separation.…
Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification. Despite the success, the huge number of parameters blocks its…
Recognition of overlapped speech has been a highly challenging task to date. State-of-the-art multi-channel speech separation system are becoming increasingly complex and expensive for practical applications. To this end, low-bit neural…
Deep learning methods have brought substantial advancements in speech separation (SS). Nevertheless, it remains challenging to deploy deep-learning-based models on edge devices. Thus, identifying an effective way to compress these large…
Split-learning (SL) has recently gained popularity due to its inherent privacy-preserving capabilities and ability to enable collaborative inference for devices with limited computational power. Standard SL algorithms assume an ideal…
The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based…
Accurately detecting dysfluencies in spoken language can help to improve the performance of automatic speech and language processing components and support the development of more inclusive speech and language technologies. Inspired by the…
This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…
Upper Mid-Band (FR3, 7-24 GHz) receivers for 6G must operate over wide bandwidths in dense spectral environments, making them particularly vulnerable to strong adjacent-band interference and front-end nonlinearities. While conventional…
PercepNet, a recent extension of the RNNoise, an efficient, high-quality and real-time full-band speech enhancement technique, has shown promising performance in various public deep noise suppression tasks. This paper proposes a new…
Error resilient tools like Packet Loss Concealment (PLC) and Forward Error Correction (FEC) are essential to maintain a reliable speech communication for applications like Voice over Internet Protocol (VoIP), where packets are frequently…
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…
The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications. One of the most popular variants of these FCNs is the `U-Net', which is an encoder-decoder…
Large-scale mobile communication systems tend to contain legacy transmission channels with narrowband bottlenecks, resulting in characteristic "telephone-quality" audio. While higher quality codecs exist, due to the scale and heterogeneity…
Neural audio codecs have recently enabled high-fidelity reconstruction at high compression rates, especially for speech. However, speech and non-speech audio exhibit fundamentally different spectral characteristics: speech energy…
MIMO processing plays a central part towards the recent increase in spectral and energy efficiencies of wireless networks. MIMO has grown beyond the original point-to-point channel and nowadays refers to a diverse range of centralized and…