90 citations · 194 across the 23 of their papers we have counts for
7 papers · 1 filter
Psychoacoustic Challenges Of Speech Enhancement On VoIP Platforms
Joseph Konan, Shikhar Agnihotri, Ojas Bhargave +4
Within the ambit of VoIP (Voice over Internet Protocol) telecommunications, the complexities introduced by acoustic transformations merit rigorous analysis. This research, rooted i…
Importance of negative sampling in weak label learning
Ankit Shah, Fuyu Tang, Zelin Ye +2
Weak-label learning is a challenging task that requires learning from data "bags" containing positive and negative instances, but only the bag labels are known. The pool of negativ…
Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents
Ziyi Yang, Shreyas S. Raman, Ankit Shah +1
Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and ge…
Improving Perceptual Quality, Intelligibility, and Acoustics on VoIP Platforms
Joseph Konan, Ojas Bhargave, Shikhar Agnihotri +12
In this paper, we present a method for fine-tuning models trained on the Deep Noise Suppression (DNS) 2020 Challenge to improve their performance on Voice over Internet Protocol (V…
Approach to Learning Generalized Audio Representation Through Batch Embedding Covariance Regularization and Constant-Q Transforms
Ankit Shah, Shuyi Chen, Kejun Zhou +2
General-purpose embedding is highly desirable for few-shot even zero-shot learning in many application scenarios, including audio tasks. In order to understand representations bett…
Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments
Jason Xinyu Liu, Ziyi Yang, Ifrah Idrees +4
Grounding navigational commands to linear temporal logic (LTL) leverages its unambiguous semantics for reasoning about long-horizon tasks and verifying the satisfaction of temporal…
Conformers are All You Need for Visual Speech Recognition
Oscar Chang, Hank Liao, Dmitriy Serdyuk +2
Visual speech recognition models extract visual features in a hierarchical manner. At the lower level, there is a visual front-end with a limited temporal receptive field that proc…