The remarkable success of deep learning in various domains relies on the availability of
large-scale annotated datasets. However, obtaining annotations is expensive and requires …

Imagine standing on a street corner in the city. With your eyes closed you can hear and
recognize a succession of sounds: cars passing by, people speaking, their footsteps when …

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 …

Audio pattern recognition is an important research topic in the machine learning area, and
includes several tasks such as audio tagging, acoustic scene classification, music …

The ability of artificial intelligence (AI) systems to perceive and comprehend audio signals is
crucial for many applications. Although significant progress has been made in this area …

Our goal is to collect a large-scale audio-visual dataset with low label noise from videosin
the wild'using computer vision techniques. The resulting dataset can be used for training …

Acoustic data provide scientific and engineering insights in fields ranging from biology and
communications to ocean and Earth science. We survey the recent advances and …

Audio event recognition, the human-like ability to identify and relate sounds from audio, is a
nascent problem in machine perception. Comparable problems such as object detection in …

Automatic speech recognition (ASR) has recently become an important challenge when
using deep learning (DL). It requires large-scale training datasets and high computational …

Convolutional Neural Networks (CNNs) have proven very effective in image classification
and show promise for audio. We use various CNN architectures to classify the soundtracks …