Buye Xu

Buye Xu

Auto-generated profile, based on publicly available information

Buye Xu

Meta Reality Labs Research

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 May 2020 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
YZYan Zhao
Yan Zhao
DWDeLiang Wang
DeLiang Wang
BXBuye Xu
Buye Xu
TZTao Zhang
Tao Zhang
In daily listening environments, human speech is often degraded by room reverberation, especially under highly reverberant conditions. Such degradation poses a challenge for many speech processing systems, where the performance becomes much worse than in anechoic environments. To combat the effect of reverberation, we propose a monaural (single-channel) speech dereverberation algorithm using temporal convolutional networks with self attention. Specifically, the proposed system includes a self-attention module to produce dynamic representations given input features, a temporal convolutional network to learn a nonlinear mapping from such representations to the magnitude spectrum of anechoic speech, and a one-dimensional (1-D) convolution module to smooth the enhanced magnitude among adjacent frames. Systematic evaluations demonstrate that the proposed algorithm improves objective metrics of speech quality in a wide range of reverberant conditions. In addition, it generalizes well to untrained reverberation times, room sizes, measured room impulse responses, real-world recorded noisy-reverberant speech, and different speakers.

22 August 2022 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Open access
ETEfthymios Tzinis
Efthymios Tzinis
YAYossi Adi
Yossi Adi
VIVamsi K. Ithapu
Vamsi K. Ithapu
BXBuye Xu
Buye Xu
PSParis Smaragdis
Paris Smaragdis
AKAnurag Kumar
Anurag Kumar
We present RemixIT, a simple yet effective self-supervised method for training speech enhancement without the need of a single isolated in-domain speech nor a noise waveform. Our approach overcomes limitations of previous methods which make them dependent on clean in-domain target signals and thus, sensitive to any domain mismatch between train and test samples. RemixIT is based on a continuous self-training scheme in which a pre-trained teacher model on out-of-domain data infers estimated pseudo-target signals for in-domain mixtures. Then, by permuting the estimated clean and noise signals and remixing them together, we generate a new set of bootstrapped mixtures and corresponding pseudo-targets which are used to train the student network. Vice-versa, the teacher periodically refines its estimates using the updated parameters of the latest student models. Experimental results on multiple speech enhancement datasets and tasks not only show the superiority of our method over prior approaches but also showcase that RemixIT can be combined with any separation model as well as be applied towards any semi-supervised and unsupervised domain adaptation task. Our analysis, paired with empirical evidence, sheds light on the inside functioning of our self-training scheme wherein the student model keeps obtaining better performance while observing severely degraded pseudo-targets.

4 June 2023
Verified
Conference Paper
Open access
AKAnurag Kumar
Anurag Kumar
KTKe Tan
Ke Tan
ZNZhaoheng Ni
Zhaoheng Ni
PMPranay Manocha
Pranay Manocha
XZXiaohui Zhang
Xiaohui Zhang
BXBuye Xu
Buye Xu
Measuring quality and intelligibility of a speech signal is usually a critical step in development of speech processing systems. To enable this, a variety of metrics to measure quality and intelligibility under different assumptions have been developed. Through this paper, we introduce tools and a set of models to estimate such known metrics using deep neural networks. These models are made available in the well-established TorchAudio library, the core audio and speech processing library within the PyTorch deep learning framework. We refer to it as TorchAudio-Squim, TorchAudio-Speech QUality and Intelligibility Measures. More specifically, in the current version of TorchAudio-squim, we establish and release models for estimating PESQ, STOI and SI-SDR among objective metrics and MOS among subjective metrics. We develop a novel approach for objective metric estimation and use a recently developed approach for subjective metric estimation. These models operate in a "referenceless" manner, that is they do not require the corresponding clean speech as reference for speech assessment. Given the unavailability of clean speech and the effortful process of subjective evaluation in real-world situations, such easy-to-use tools would greatly benefit speech processing research and development.

11 December 2020 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
KTKe Tan
Ke Tan
BXBuye Xu
Buye Xu
AKAnurag Kumar
Anurag Kumar
ENEliya Nachmani
Eliya Nachmani
YAYossi Adi
Yossi Adi
Most existing deep learning based binaural speaker separation systems focus on producing a monaural estimate for each of the target speakers, and thus do not preserve the interaural cues, which are crucial for human listeners to perform sound localization and lateralization. In this study, we address talker-independent binaural speaker separation with interaural cues preserved in the estimated binaural signals. Specifically, we extend a newly-developed gated recurrent neural network for monaural separation by additionally incorporating self-attention mechanisms and dense connectivity. We develop an end-to-end multiple-input multiple-output system, which directly maps from the binaural waveform of the mixture to those of the speech signals. The experimental results show that our proposed approach achieves significantly better separation performance than a recent binaural separation approach. In addition, our approach effectively preserves the interaural cues, which improves the accuracy of sound localization.

1 May 2023 in The Journal of the Acoustical Society of America
Verified
Journal Article
Open access
PDF file
TXTong Xiao
Tong Xiao
BXBuye Xu
Buye Xu
CZChuming Zhao
Chuming Zhao
Active noise control (ANC) systems are commonly designed to achieve maximal sound reduction regardless of the incident direction of the sound. When desired sound is present, the state-of-the-art methods add a separate system to reconstruct it. This can result in distortion and latency. In this work, we propose a multi-channel ANC system that only reduces sound from undesired directions, and the system truly preserves the desired sound instead of reproducing it. The proposed algorithm imposes a spatial constraint on the hybrid ANC cost function to achieve spatial selectivity. Based on a six-channel microphone array on a pair of augmented eyeglasses, results show that the system minimized only noise coming from undesired directions. The control performance could be maintained even when the array was heavily perturbed. The proposed algorithm was also compared with the existing methods in the literature. Not only did the proposed system provide better noise reduction, but it also required much less effort. The binaural localization cues did not need to be reconstructed since the system preserved the physical sound wave from the desired source.

7 May 2025 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
VKVahid Ahmadi Kalkhorani
Vahid Ahmadi Kalkhorani
CYCheng Yu
Cheng Yu
AKAnurag Kumar
Anurag Kumar
KTKe Tan
Ke Tan
BXBuye Xu
Buye Xu
DWDeLiang Wang
DeLiang Wang
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. AV-CrossNet is extended from the TF-CrossNet architecture, which is a recently proposed network that performs complex spectral mapping for speech separation by leveraging global attention and positional encoding. To effectively utilize visual cues, the proposed system incorporates pre-extracted visual embeddings and employs a visual encoder comprising temporal convolutional layers. Audio and visual features are fused in an early fusion layer before feeding to AV-CrossNet blocks. We evaluate AV-CrossNet on multiple datasets, including LRS, VoxCeleb, TCD-TIMIT, and COG-MHEAR challenge, in terms of the performance metrics of PESQ, STOI, SNR and SDR. Evaluation results demonstrate that AV-CrossNet advances the state-of-the-art performance in all audiovisual tasks, even on untrained and mismatched datasets.