Abstract | ||
---|---|---|
Detecting and identifying emotions expressed in speech signals is a very complex task that generally requires processing a large sample size to extract intricate details and match the diversity of human expression in speech. There is not an emotional dataset commonly accepted as a standard test bench to evaluate the performance of the supervised machine learning algorithms when presented with extracted speech characteristics. This work proposes a generic platform to capture and validate emotional speech. The aim of the platform is collaborative-crowdsourcing and it can be used for any language (currently, it is available in four languages such as Spanish, English, German and French). As an example, a module for elicitation of stress in speech through a set of online interviews and other module for labeling recorded speech have been developed. This study is envisaged as the beginning of an effort to establish a large, cost-free standard speech corpus to assess emotions across multiple languages. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-19591-5_16 | UNDERSTANDING THE BRAIN FUNCTION AND EMOTIONS, PT I |
Keywords | Field | DocType |
Characterizing stress, Data acquisition, Stress behavior in human-computer interaction, Cooperative framework, Emotional stress | Speech corpus,Test bench,Computer science,Data acquisition,Speech characteristics,Artificial intelligence,Natural language processing,Sample size determination,Machine learning,German | Conference |
Volume | ISSN | Citations |
11486 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Palacios-Alonso | 1 | 11 | 5.43 |
J. Carlos Lázaro-Carrascosa | 2 | 0 | 0.68 |
Agustín López-Arribas | 3 | 0 | 0.34 |
Guillermo Meléndez-Morales | 4 | 0 | 0.34 |
Andrés Gómez-Rodellar | 5 | 3 | 3.11 |
Andrés Loro-Álavez | 6 | 0 | 0.34 |
Victor Nieto Lluis | 7 | 59 | 14.14 |
María Victoria Rodellar Biarge | 8 | 44 | 13.67 |
Athanasios Tsanas | 9 | 0 | 0.68 |
Pedro Gómez Vilda | 10 | 289 | 52.48 |