Computational Analysis of Sound Scenes and Events

By Tuomas Virtanen, Mark D. Plumbley, D. Ellis. 2017

281 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Signal Processing

Citations in the corpus

FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, background): “A high quality evaluation set must be comprehensive, varied, and representative [68], while being free from contamination from the development set in order to allow testing models’ generalization capabilities.”
USM-SED - A Dataset for Polyphonic Sound Event Detection in Urban Sound Monitoring Scenarios (2021, background): “Sound event detection (SED) is a crucial step in the analysis of polyphonic soundscapes, which surround us every day [1].”
SeCoST: Sequential Co-Supervision for Weakly Labeled Audio Event Detection (2019, background): “While several classical machine learning and deep learning methods have been developed for AED using strong labels [2], [1], [3], [4], much of the recent progress has focused on efﬁciently leveraging weakly labeled data [5].”
Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Masking (2020, background): “As Sound Event Recognition (SER) has gained increasing attention in recent years [1], research in this ﬁeld has moved from small datasets encompassing few hours of audio [2, 3, 4, 5], to larger datasets with much greater coverage and duration [6, 7].”
Audio tagging with noisy labels and minimal supervision (2019, background): “Environmental sound recognition has gained increasing attention in recent years, encompassing tasks such as acoustic scene classiﬁcation, sound event detection or audio tagging [1].”
Separate Anything You Describe (2023, unknown): “sound separation aims to separate real-world sound recordings into individual source tracks, also known as the “cocktail party problem” [2].”
Improving Sound Event Detection in Domestic Environments using Sound Separation (2020, background): “Sound event detection (SED) is the task of describing, from an audio recording, what happens and when each single sound event is occurring [1].”
Convolutional Recurrent Neural Network and Data Augmentation for Audio Tagging with Noisy Labels and Minimal Supervision (2019, background): “Within environmental sound recognition the tasks of Sound Event Detection (SED), Audio Tagging and Acoustic Scene Classiﬁcation (ASC) [1] can be distinguished, which differ in the level of detail obtained about the acoustic environment.”
Sound Event Detection in Synthetic Domestic Environments (2020, unknown): “We are constantly surrounded by sounds and we rely heavily on these sounds to obtain important information about what is happening around us [1].”
Large Scale Audiovisual Learning of Sounds with Weakly Labeled Data (2020, methodology): “However, most prior work on sound recognition focuses on learning to recognize sounds only from audio [Virtanen et al., 2017; Kumar, 2018].”
Machine learning in acoustics: Theory and applications. (2019, background): “243 There is another reason that algorithms which parse nat-ural acoustic scenes are of special interest.”
A Simple Fusion of Deep and Shallow Learning for Acoustic Scene Classification (2018, background): “ttempt to automatize it. One of the goals of machine listening is to have systems that perform similarly as humans in tasks like this, which is receiving growing attention from the research community [1]. The consecutive editions of the Detection and Classiﬁcation of Acoustic Scenes and Events (DCAS”
Limitations of Weak Labels for Embedding and Tagging (2020, background): “In recent years, interest in ambient sound analysis has grown in particular due to the numerous potential applications [1].”
Automatic Music Transcription: An Overview (2019, methodology): “While everyday and natural sounds do not exhibit the same degree of temporal regularity and inter-source frequency dependence as found in music signals, there are close interactions between the two problems in terms of the methodologies used, as observed in the literature [6].”