A transfer learning framework for predicting the emotional content of generalized sound events

Ntalampiras, Stavros

doi:10.1121/1.4977749

Cited by 28 publications

(10 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a jointly created space may offer improved prediction in multiple applications domains. To this end, we intent to exploit transfer learning technologies [12] forming a synergistic framework able to incorporate and transfer knowledge coming from multiple domains favoring diverse applications, such as music information retrieval, bioacoustic signal processing, etc.…”

Section: Resultsmentioning

confidence: 99%

Emotional quantification of soundscapes by learning between samples

Ntalampiras

2020

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Predicting the emotional responses of humans to soundscapes is a relatively recent field of research coming with a wide range of promising applications. This work presents the design of two convolutional neural networks, namely ArNet and ValNet, each one responsible for quantifying arousal and valence evoked by soundscapes. We build on the knowledge acquired from the application of traditional machine learning techniques on the specific domain, and design a suitable deep learning framework. Moreover, we propose the usage of artificially created mixed soundscapes, the distributions of which are located between the ones of the available samples, a process that increases the variance of the dataset leading to significantly better performance. The reported results outperform the state of the art on a soundscape dataset following Schafer’s standardized categorization considering both sound’s identity and the respective listening context.

show abstract

Section: Resultsmentioning

confidence: 99%

Emotional quantification of soundscapes by learning between samples

Ntalampiras

2020

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…Identification of the emotion on the listener's side may be indicative of the respective human reaction. To this end, appropriate signal processing and pattern recognition algorithms can by employed [19].…”

Section: Future Perspectives: Machine Learning For Mir Purposesmentioning

confidence: 99%

Preservation and Promotion of Opera Cultural Heritage: The Experience of La Scala Theatre

Avanzini

Baratè

Haus

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

This paper focuses on music and music-related cultural heritage typically preserved by opera houses, starting from the experience achieved during the long-lasting collaboration between La Scala theater and the Laboratory of Music Informatics of the University of Milan. First, we will mention the most significant results achieved by the project in the fields of preservation, information retrieval and dissemination of cultural heritage through computer-based approaches. Moreover, we will discuss the possibilities offered by new technologies applied to the conservative context of an opera house, including: the multi-layer representation of music information to foster the accessibility of musical content also by non-experts; the adoption of 5G networks to deliver spherical videos of live events, thus opening new scenarios for cultural heritage enjoyment and dissemination; deep learning approaches both to improve internal processes (e.g., back-office applications for music information retrieval) and to offer advanced services to users (e.g., highly-customized experiences).

show abstract

“…Following the recent findings in the specific field, we used acoustic parameters able to capture characteristics associated with the context, i.e. mel-frequency cepstral coefficients and temporal modulation [17,18,19,20] modeled by means of both generative (having at their core the hidden Markov model technology) and discriminative (support vector machines [21] and echo state networks [22]) pattern recognition algorithms. Unlike deep learning techniques, which are typically characterized by low interpretability levels [23], we aimed at a comprehensive classification scheme potentially revealing useful information about the problem at hand.…”

Section: Introductionmentioning

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

A transfer learning framework for predicting the emotional content of generalized sound events

Cited by 28 publications

References 32 publications

Emotional quantification of soundscapes by learning between samples

Emotional quantification of soundscapes by learning between samples

Preservation and Promotion of Opera Cultural Heritage: The Experience of La Scala Theatre

Automatic Classification of Cat Vocalizations Emitted in Different Contexts

Contact Info

Product

Resources

About