1 code implementation • 2 Sep 2020 • Ke Tan, Buye Xu, Anurag Kumar, Eliya Nachmani, Yossi Adi
In addition, our approach effectively preserves the interaural cues, which improves the accuracy of sound localization.
Audio and Speech Processing Sound
no code implementations • 29 May 2021 • Pranay Manocha, Anurag Kumar, Buye Xu, Anjali Menon, Israel D. Gebru, Vamsi K. Ithapu, Paul Calamia
Subjective evaluations are critical for assessing the perceptual realism of sounds in audio-synthesis driven technologies like augmented and virtual reality.
no code implementations • 25 Jun 2021 • Ori Kabeli, Yossi Adi, Zhenyu Tang, Buye Xu, Anurag Kumar
Our stateful implementation for online separation leads to a minor drop in performance compared to the offline model; 0. 8dB for monaural inputs and 0. 3dB for binaural inputs while reaching a real-time factor of 0. 65.
no code implementations • 11 Sep 2021 • Yangyang Xia, Buye Xu, Anurag Kumar
Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training.
1 code implementation • NeurIPS 2021 • Pranay Manocha, Buye Xu, Anurag Kumar
We show that neural networks trained using our framework produce scores that correlate well with subjective mean opinion scores (MOS) and are also competitive to methods such as DNSMOS, which explicitly relies on MOS from humans for training networks.
1 code implementation • 19 Oct 2021 • Efthymios Tzinis, Yossi Adi, Vamsi K. Ithapu, Buye Xu, Anurag Kumar
Specifically, a separation teacher model is pre-trained on an out-of-domain dataset and is used to infer estimated target signals for a batch of in-domain mixtures.
2 code implementations • 17 Feb 2022 • Efthymios Tzinis, Yossi Adi, Vamsi Krishna Ithapu, Buye Xu, Paris Smaragdis, Anurag Kumar
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.
no code implementations • 24 Jun 2022 • Pranay Manocha, Anurag Kumar, Buye Xu, Anjali Menon, Israel D. Gebru, Vamsi K. Ithapu, Paul Calamia
Audio quality assessment is critical for assessing the perceptual realism of sounds.
no code implementations • 22 Aug 2022 • Tong Xiao, Buye Xu, Chuming Zhao
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.
no code implementations • 16 Nov 2022 • Kuan-Lin Chen, Daniel D. E. Wong, Ke Tan, Buye Xu, Anurag Kumar, Vamsi Krishna Ithapu
During training, our approach augments a model learning complex spectral mapping with a temporary submodel to predict the covariance of the enhancement error at each time-frequency bin.
no code implementations • 20 Nov 2022 • Rodrigo Mira, Buye Xu, Jacob Donley, Anurag Kumar, Stavros Petridis, Vamsi Krishna Ithapu, Maja Pantic
Audio-visual speech enhancement aims to extract clean speech from a noisy environment by leveraging not only the audio itself but also the target speaker's lip movements.
no code implementations • 11 Jan 2023 • Haibin Wu, Ke Tan, Buye Xu, Anurag Kumar, Daniel Wong
By comparing complex- and real-valued versions of fundamental building blocks in the recently developed gated convolutional recurrent network (GCRN), we show how different mechanisms for basic blocks affect the performance.
no code implementations • 4 Apr 2023 • Anurag Kumar, Ke Tan, Zhaoheng Ni, Pranay Manocha, Xiaohui Zhang, Ethan Henderson, Buye Xu
To enable this, a variety of metrics to measure quality and intelligibility under different assumptions have been developed.
no code implementations • 3 Mar 2024 • Ravi Shankar, Ke Tan, Buye Xu, Anurag Kumar
Self-supervised learned models have been found to be very effective for certain speech tasks such as automatic speech recognition, speaker identification, keyword spotting and others.