Audio and acoustics

Publication

SoundTRC: DNN-based Acoustic Target Region Control

Yuhang He, Andrew Markham, Okan Köpüklü

International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025) | April 2025

Publication

Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality Assessment

Benjamin Stahl, Hannes Gamper

2025 International Conference on Acoustics, Speech, and Signal Processing | April 2025

Publication

Make Some Noise: Towards LLM audio reasoning and generation using sound tokens

Shivam Mehta, Nebojsa Jojic, Hannes Gamper

2025 International Conference on Acoustics, Speech, and Signal Processing | April 2025

Publication

Ultra-Low Latency Speech Enhancement -A Comprehensive Study

Haibin Wu, Sebastian Braun

2025 International Conference on Acoustics, Speech, and Signal Processing | April 2025

Project

Publication

Automated Feature Engineering for Single-Trial EEG and Eye-Tracking Classification in Predictive Text Interfaces

Ard Kastrati, R. Michael Winters, Nemanja Djuric, Ivan Tashev, Yu-Te Wang

13th International Winter Conference on Brain-Computer Interface (BCI) | February 2025

Project

Publication

ICASSP 2024 Speech Signal Improvement Challenge

Nicolae-Cătălin Ristea, Babak Naderi, Ando Saabas, Ross Cutler, Sebastian Braun, Solomiya Branets

IEEE Open Journal of Signal Processing | January 2025, Vol 6: pp. 1-9

Publication

Hearable devices with sound bubbles

Tuochao Chen, Malek Itani, Sefik Emre Eskimez, Takuya Yoshioka, Shyamnath Gollakota

Nature Electronics | November 2024, pp. 1-12

Publication

Whispering Wearables: Multimodal Approach to Silent Speech Recognition with Head-Worn Devices

Tanmay Srivastava, R. Michael Winters, Yu-Te Wang, Thomas M. Gable, Teresa LaScala, Ivan Tashev

International Conference on Multimodal Interaction | November 2024

Project

Microsoft Research Blog

Research Focus: Week of October 7, 2024

October 9, 2024

Simplifying secure decision tree training; Improving accuracy of audio content detection; A novel neurosymbolic system for converting text to tables; New video series: AI for Business Transformation; TEE security protections for container workloads.

Group

Interactive Multimodal AI Systems (IMAIS)

The Interactive Multimodal AI Systems focuses on creating interactive systems and experiences that blend the richness and complexity of people and their real, physical world with advanced technology. We seek to leverage multimodal generative AI…