Strength Is in Numbers: Can Concordant Artificial Listeners Improve Prediction of Emotion from Speech?
Humans can communicate their emotions by modulating facial expressions or the tone of their voice. Albeit numerous applications exist that enable machines to read facial emotions and recognize the content of verbal messages, methods for speech emotion recognition are still in their infancy. Yet, fas...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2016-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC5001724?pdf=render |
| _version_ | 1819291484890857472 |
|---|---|
| author | Eugenio Martinelli Arianna Mencattini Elena Daprati Corrado Di Natale |
| author_facet | Eugenio Martinelli Arianna Mencattini Elena Daprati Corrado Di Natale |
| author_sort | Eugenio Martinelli |
| collection | DOAJ |
| description | Humans can communicate their emotions by modulating facial expressions or the tone of their voice. Albeit numerous applications exist that enable machines to read facial emotions and recognize the content of verbal messages, methods for speech emotion recognition are still in their infancy. Yet, fast and reliable applications for emotion recognition are the obvious advancement of present 'intelligent personal assistants', and may have countless applications in diagnostics, rehabilitation and research. Taking inspiration from the dynamics of human group decision-making, we devised a novel speech emotion recognition system that applies, for the first time, a semi-supervised prediction model based on consensus. Three tests were carried out to compare this algorithm with traditional approaches. Labeling performances relative to a public database of spontaneous speeches are reported. The novel system appears to be fast, robust and less computationally demanding than traditional methods, allowing for easier implementation in portable voice-analyzers (as used in rehabilitation, research, industry, etc.) and for applications in the research domain (such as real-time pairing of stimuli to participants' emotional state, selective/differential data collection based on emotional content, etc.). |
| first_indexed | 2024-12-24T03:39:23Z |
| format | Article |
| id | doaj.art-8525792585f9414d9ac0b292de19799b |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-24T03:39:23Z |
| publishDate | 2016-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-8525792585f9414d9ac0b292de19799b2022-12-21T17:16:58ZengPublic Library of Science (PLoS)PLoS ONE1932-62032016-01-01118e016175210.1371/journal.pone.0161752Strength Is in Numbers: Can Concordant Artificial Listeners Improve Prediction of Emotion from Speech?Eugenio MartinelliArianna MencattiniElena DapratiCorrado Di NataleHumans can communicate their emotions by modulating facial expressions or the tone of their voice. Albeit numerous applications exist that enable machines to read facial emotions and recognize the content of verbal messages, methods for speech emotion recognition are still in their infancy. Yet, fast and reliable applications for emotion recognition are the obvious advancement of present 'intelligent personal assistants', and may have countless applications in diagnostics, rehabilitation and research. Taking inspiration from the dynamics of human group decision-making, we devised a novel speech emotion recognition system that applies, for the first time, a semi-supervised prediction model based on consensus. Three tests were carried out to compare this algorithm with traditional approaches. Labeling performances relative to a public database of spontaneous speeches are reported. The novel system appears to be fast, robust and less computationally demanding than traditional methods, allowing for easier implementation in portable voice-analyzers (as used in rehabilitation, research, industry, etc.) and for applications in the research domain (such as real-time pairing of stimuli to participants' emotional state, selective/differential data collection based on emotional content, etc.).http://europepmc.org/articles/PMC5001724?pdf=render |
| spellingShingle | Eugenio Martinelli Arianna Mencattini Elena Daprati Corrado Di Natale Strength Is in Numbers: Can Concordant Artificial Listeners Improve Prediction of Emotion from Speech? PLoS ONE |
| title | Strength Is in Numbers: Can Concordant Artificial Listeners Improve Prediction of Emotion from Speech? |
| title_full | Strength Is in Numbers: Can Concordant Artificial Listeners Improve Prediction of Emotion from Speech? |
| title_fullStr | Strength Is in Numbers: Can Concordant Artificial Listeners Improve Prediction of Emotion from Speech? |
| title_full_unstemmed | Strength Is in Numbers: Can Concordant Artificial Listeners Improve Prediction of Emotion from Speech? |
| title_short | Strength Is in Numbers: Can Concordant Artificial Listeners Improve Prediction of Emotion from Speech? |
| title_sort | strength is in numbers can concordant artificial listeners improve prediction of emotion from speech |
| url | http://europepmc.org/articles/PMC5001724?pdf=render |
| work_keys_str_mv | AT eugeniomartinelli strengthisinnumberscanconcordantartificiallistenersimprovepredictionofemotionfromspeech AT ariannamencattini strengthisinnumberscanconcordantartificiallistenersimprovepredictionofemotionfromspeech AT elenadaprati strengthisinnumberscanconcordantartificiallistenersimprovepredictionofemotionfromspeech AT corradodinatale strengthisinnumberscanconcordantartificiallistenersimprovepredictionofemotionfromspeech |