Forest ecosystems are of paramount importance to the sustainable existence of life on earth.
Unique natural and artificial phenomena pose severe threats to the perseverance of such …

In the domain of audio processing, Transfer Learning has facilitated the rise of Self-
Supervised Learning and Zero-Shot Learning techniques. These approaches have led to …

The Internet of Audio Things (IoAuT) is an emerging research field positioned at the
intersection of the Internet of Things, sound and music computing, artificial intelligence, and …

We present SoundStream, a novel neural audio codec that can efficiently compress speech,
music and general audio at bitrates normally targeted by speech-tailored codecs …

Most existing datasets for sound event recognition (SER) are relatively small and/or domain-
specific, with the exception of AudioSet, based on over 2 M tracks from YouTube videos and …

Factory machinery is prone to failure or breakdown, resulting in significant expenses for
companies. Hence, there is a rising interest in machine monitoring using different sensors …

We explore the problem of Audio Captioning: generating natural language description for
any kind of audio in the wild, which has been surprisingly unexplored in previous research …

Recently audio and video material has been used significantly in various online platforms.
The au-dio-video materials enhance the teaching and learning process by facilitating the …

In recent years, rapid progress has been made on the problem of single-channel sound
separation using supervised training of deep neural networks. In such supervised …

This paper introduces a new dataset called" ToyADMOS" designed for anomaly detection in
machine operating sounds (ADMOS). To the best our knowledge, no large-scale datasets …