AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition

no code implementations • 18 Jan 2024 • Ju Lin, Niko Moritz, Yiteng Huang, Ruiming Xie, Ming Sun, Christian Fuegen, Frank Seide

Wearable devices like smart glasses are approaching the compute capability to seamlessly generate real-time closed captions for live conversations.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding

no code implementations • 22 Jul 2023 • Suyoun Kim, Akshat Shrivastava, Duc Le, Ju Lin, Ozlem Kalinli, Michael L. Seltzer

End-to-end (E2E) spoken language understanding (SLU) systems that generate a semantic parse from speech have become more promising recently.

speech-recognition Speech Recognition +1

Egocentric Audio-Visual Noise Suppression

no code implementations • 7 Nov 2022 • Roshan Sharma, Weipeng He, Ju Lin, Egor Lakomkin, Yang Liu, Kaustubh Kalgaonkar

In this paper, we first demonstrate that egocentric visual information is helpful for noise suppression.

Action Classification Event Detection +3

Deep Learning for Needle Detection in a Cannulation Simulator

1 code implementation • 5 May 2021 • Jianxin Gao, Ju Lin, Irfan Kil, Ravikiran B. Singapogu, Richard E. Groff

The CRNN was implemented in real time on commodity hardware for use in the cannulation simulator, and the performance was verified.

Speech Enhancement Using Multi-Stage Self-Attentive Temporal Convolutional Networks

no code implementations • 24 Feb 2021 • Ju Lin, Adriaan J. van Wijngaarden, Kuang-Ching Wang, Melissa C. Smith

The resulting multi-stage speech enhancement system, in short, multi-stage SA-TCN, is compared with state-of-the-art deep-learning speech enhancement methods using the LibriSpeech and VCTK data sets.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2