Introduction to acoustic event and scene analysis

Imoto, Keisuke

doi:10.1250/ast.39.182

Cited by 44 publications

(23 citation statements)

References 38 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section provides thorough details regarding the parameterization of the proposed framework for classifying cat vocalizations, as well as the respective experimental results and how these compare with classification systems commonly used in the generalized sound classification literature [44], i.e., class-specific and universal HMMs, support vector machines, and echo state networks. The motivation behind these choices aimed at satisfying the condition of including both generative and discriminative pattern recognition schemes [45,46]. Moreover, during early experimentations, it was verified that MFCCs and temporal modulation features capture distinct properties of the structure of the available audio signals as they achieved different recognition rates characterized by diverse mislassifications, thus we decided to use them concurrently.…”

Section: Experimental Set-up and Resultsmentioning

confidence: 99%

Automatic Classification of Cat Vocalizations Emitted in Different Contexts

Ntalampiras

Ludovico

Presti

et al. 2019

Animals

View full text Add to dashboard Cite

Cats employ vocalizations for communicating information, thus their sounds can carry a widerange of meanings. Concerning vocalization, an aspect of increasing relevance directly connected withthe welfare of such animals is its emotional interpretation and the recognition of the production context.To this end, this work presents a proof of concept facilitating the automatic analysis of cat vocalizationsbased on signal processing and pattern recognition techniques, aimed at demonstrating if the emissioncontext can be identified by meowing vocalizations, even if recorded in sub-optimal conditions. Werely on a dataset including vocalizations of Maine Coon and European Shorthair breeds emitted in threedifferent contexts: waiting for food, isolation in unfamiliar environment, and brushing. Towards capturing theemission context, we extract two sets of acoustic parameters, i.e., mel-frequency cepstral coefficients andtemporal modulation features. Subsequently, these are modeled using a classification scheme based ona directed acyclic graph dividing the problem space. The experiments we conducted demonstrate thesuperiority of such a scheme over a series of generative and discriminative classification solutions. Theseresults open up new perspectives for deepening our knowledge of acoustic communication betweenhumans and cats and, in general, between humans and animals.

show abstract

Section: Experimental Set-up and Resultsmentioning

confidence: 99%

Automatic Classification of Cat Vocalizations Emitted in Different Contexts

Ntalampiras

Ludovico

Presti

et al. 2019

Animals

View full text Add to dashboard Cite

show abstract

“…Conventional CRNN-based approaches achieve reasonable event detection performances when there is a sufficient amount of training sound data. However, since recording and annotating environmental sounds are very timeconsuming [1], in many situations, the conventional CRNNbased methods are likely to exhibit degradation in their event detection performance. To address this limitation, we propose a new method of SED using graph Laplacian regularization based on sound event co-occurrence.…”

Section: Motivationmentioning

confidence: 99%

“…Sound event detection (SED) is a task that identifies types of sound and detects their onset and offset [1]. Recently, many works have addressed SED because SED has a large potential for many applications such as monitoring elderly people or infants [2], [3], automatic surveillance [4]- [6], automatic anomaly detection [7], [8], and media retrieval [9].…”

Section: Introductionmentioning

confidence: 99%

Sound Event Detection Utilizing Graph Laplacian Regularization with Event Co-Occurrence

Imoto

Kyochi

2020

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

A limited number of types of sound event occur in an acoustic scene and some sound events tend to co-occur in the scene; for example, the sound events "dishes" and "glass jingling" are likely to cooccur in the acoustic scene "cooking." In this paper, we propose a method of sound event detection using graph Laplacian regularization with sound event co-occurrence taken into account. In the proposed method, the occurrences of sound events are expressed as a graph whose nodes indicate the frequencies of event occurrence and whose edges indicate the sound event co-occurrences. This graph representation is then utilized for the model training of sound event detection, which is optimized under an objective function with a regularization term considering the graph structure of sound event occurrence and co-occurrence. Evaluation experiments using the TUT Sound Events 2016 and 2017 detasets, and the TUT Acoustic Scenes 2016 dataset show that the proposed method improves the performance of sound event detection by 7.9 percentage points compared with the conventional CNN-BiGRU-based detection method in terms of the segment-based F1 score. In particular, the experimental results indicate that the proposed method enables the detection of co-occurring sound events more accurately than the conventional method.

show abstract

“…To understand the sounds that occur in a given environment, researchers have developed four major back‐end processing approaches to analyzing acoustic scenes and sound events: (i) ASC, (ii) audio tagging, (iii) SED and (iv) anomalous sound detection . In this section, we introduce each problem setting and describe typical approaches for conducting these tasks.…”

Section: Back‐end Techniques For Environmental Sound Processingmentioning

confidence: 99%

Environmental sound processing and its applications

Miyazaki

Toda

Hayashi

et al. 2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

As part of the effort to develop techniques for understanding environments using sound, many studies in the field of computational auditory scene analysis have focused on using computers to perform functions carried out naturally by the human auditory system. Thanks to recent progress in machine‐learning techniques, these environmental sound‐processing techniques have significantly improved and a widening variety of applications has resulted in considerable interest in this field. In this review, we introduce the fundamental techniques of environmental sound processing, as well as recent advances in front‐end and back‐end processing and potential applications for these techniques. Prospects for further progress in the field of environmental sound processing and the challenges still to be overcome are also discussed. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

Introduction to acoustic event and scene analysis

Cited by 44 publications

References 38 publications

Automatic Classification of Cat Vocalizations Emitted in Different Contexts

Automatic Classification of Cat Vocalizations Emitted in Different Contexts

Sound Event Detection Utilizing Graph Laplacian Regularization with Event Co-Occurrence

Environmental sound processing and its applications

Contact Info

Product

Resources

About