Search Results for author: Ke Tan

Found 10 papers, 1 papers with code

A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement

no code implementations3 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.

Automatic Speech Recognition Keyword Spotting +5

Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment

no code implementations6 Dec 2023 Fei Yang, Shuang Peng, Ning Sun, Fangyu Wang, Ke Tan, Fu Wu, Jiezhong Qiu, Aimin Pan

Large language models (LLMs) such as GPT-3, OPT, and LLaMA have demonstrated remarkable accuracy in a wide range of tasks.

Scheduling

TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio

no code implementations4 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.

Rethinking complex-valued deep neural networks for monaural speech enhancement

no code implementations11 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.

Open-Ended Question Answering Speech Enhancement

Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement

no code implementations16 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.

Speech Enhancement

Location-based training for multi-channel talker-independent speaker separation

no code implementations8 Oct 2021 Hassan Taherian, Ke Tan, DeLiang Wang

We further demonstrate the effectiveness of LBT for the separation of four and five concurrent speakers.

Speaker Separation

SAGRNN: Self-Attentive Gated RNN for Binaural Speaker Separation with Interaural Cue Preservation

1 code implementation2 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

Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network

no code implementations16 Sep 2019 Ke Tan, Yong Xu, Shi-Xiong Zhang, Meng Yu, Dong Yu

Background noise, interfering speech and room reverberation frequently distort target speech in real listening environments.

Audio and Speech Processing Sound Signal Processing

Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling

no code implementations11 Mar 2019 Peidong Wang, Ke Tan, DeLiang Wang

In this study, we analyze the distortion problem, compare different acoustic models, and investigate a distortion-independent training scheme for monaural speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective

no code implementations22 Nov 2018 Zhong-Qiu Wang, Ke Tan, DeLiang Wang

This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain.

Speaker Separation

Cannot find the paper you are looking for? You can Submit a new open access paper.