activity
20152022
most citedNORESQA: A Framework for Speech Quality Assessment using Non-Matching References

24 citations · 51 across the 7 of their papers we have counts for

collaborators
Showing cs.SDShow all

9 papers · 1 filter

cs.SD2022

The impact of removing head movements on audio-visual speech enhancement

Zhiqi Kang, Mostafa Sadeghi, Radu Horaud +3

This paper investigates the impact of head movements on audio-visual speech enhancement (AVSE). Although being a common conversational feature, head movements have been ignored by…

cs.SD2021

Do sound event representations generalize to other audio tasks? A case study in audio transfer learning

Anurag Kumar, Yun Wang, Vamsi Krishna Ithapu +1

Transfer learning is critical for efficient information transfer across multiple related learning problems. A simple, yet effective transfer learning approach utilizes deep neural…

cs.SD202020 cited

A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition

Anurag Kumar, Vamsi Krishna Ithapu

An important problem in machine auditory perception is to recognize and detect sound events. In this paper, we propose a sequential self-teaching approach to learning sounds. Our m…

cs.SD2019

Secost: Sequential co-supervision for large scale weakly labeled audio event detection

Anurag Kumar, Vamsi Krishna Ithapu

Weakly supervised learning algorithms are critical for scaling audio event detection to several hundreds of sound categories. Such learning models should not only disambiguate soun…

cs.SD2018

Learning Sound Events From Webly Labeled Data

Anurag Kumar, Ankit Shah, Bhiksha Raj +1

In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for soun…

cs.SD2018

A Closer Look at Weak Label Learning for Audio Events

Ankit Shah, Anurag Kumar, Alexander G. Hauptmann +1

Audio content analysis in terms of sound events is an important research problem for a variety of applications. Recently, the development of weak labeling approaches for audio or s…