illustration of a speaker and soundwaves on top of a computer on a green gradient background

Audio and acoustics

Audio and Acoustics Research Group

Audio and Acoustics Research Group

diagram

CoVoMix: Advancing Zero-shot Speech Generation for Human-like Multi-talker Conversation

What’s Your Story: Ivan Tashev

TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation

TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation

Current selections

Sort by: Most recent

Clear selections

Publication

Unsupervised Deep Representation Learning to Remove Motion Artifacts in Free-mode Body Sensor Networks

Shuayb Zarar, Ivan Tashev

IEEE Int. Conf. Wearable and Implantable Body Sensor Networks (BSN) | May 2017

Publication

Robust harmonic features for classification-based pitch estimation

IEEE/ACM Transactions on Audio, Speech, and Language Processing | May 2017, Vol 25(5): pp. 952-964

Publication

A Statistical Approach to Semi-supervised Speech Enhancement with Low-order Non Negative Matrix Factorization

Shuayb Zarar, Ivan Tashev

IEEE Int. Conf. Acoustics Speech and Signal Processing (ICASSP) | March 2017

Publication

Learning Utterance-level Representations for Speech Emotion and Age/Gender Recognition Using Deep Neural Networks

Zhong-Qiu Wang, Ivan Tashev

Proc. ICASSP | March 2017

Publication

Ultrasound-based Gesture Recognition

Amit Das, Ivan Tashev, Shuayb Zarar

IEEE Int. Conf. Acoustics Speech and Signal Processing (ICASSP) | March 2017

Project Project

Publication

Interaural time delay personalisation using incomplete head scans

Hannes Gamper, David Johnston, Ivan Tashev

Proc. ICASSP | March 2017

Publication

Cost Function for Sound Source Localization with Arbitrary Microphone Arrays

Ivan Tashev, Long Le, Vani Gopalakrishna, Andrew Lovitt

Proc. HSCMA | March 2017

Publication

Clock drift estimation and compensation for asynchronous impulse response measurements

Proc. Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA) | March 2017

Publication

Online Meeting Recognition in Noisy Environments with Time-Frequency Mask Based MVDR Beamforming

Shoko Araki, Nobutaka Ito, Marc Delcroix, Atsunori Ogawa, Keisuke Kinoshita, Takuya Higuchi, Takuya Yoshioka, Dong Tran, Shigeki Karita, Tomohiro Nakatani

HSCMA 2017 | March 2017

Project

Neural Networks-based Speech Enhancement

The goal of speech enhancement is to take the audio signal from a microphone, clean it and forward clean audio to multiple clients such as speech-recognition software, archival databases and speakers.