| 1 |
End-to-End Speech Emotion Recognition: Challenges of Real-Life Emergency Call Centers Data Recordings
|
|
|
|
In: ISBN: 978-1-6654-0019-0 ; 2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII) ; https://hal.archives-ouvertes.fr/hal-03405970 ; 2021 9th International Conference on Affective Computing and Intelligent Interaction (ACII), Sep 2021, Nara, Japan ; https://www.acii-conf.net/2021/ (2021)
|
|
Abstract:
International audience ; Recognizing a speaker's emotion from their speech can be a key element in emergency call centers. End-to-end deep learning systems for speech emotion recognition now achieve equivalent or even better results than conventional machine learning approaches. In this paper, in order to validate the performance of our neural network architecture for emotion recognition from speech, we first trained and tested it on the widely used corpus accessible by the community, IEMOCAP. We then used the same architecture as the real life corpus, CEMO, composed of 440 dialogs (2h16m) from 485 speakers. The most frequent emotions expressed by callers in these real life emergency dialogues are fear, anger and positive emotions such as relief. In the IEMOCAP general topic conversations, the most frequent emotions are sadness, anger and happiness. Using the same end-to-end deep learning architecture, an Unweighted Accuracy Recall (UA) of 63% is obtained on IEMOCAP and a UA of 45.6% on CEMO, each with 4 classes. Using only 2 classes (Anger, Neutral), the results for CEMO are 76.9% UA compared to 81.1% UA for IEMOCAP. We expect that these encouraging results with CEMO can be improved by combining the audio channel with the linguistic channel. Real-life emotions are clearly more complex than acted ones, mainly due to the large diversity of emotional expressions of speakers. Index Terms-emotion detection, end-to-end deep learning architecture, call center, real-life database, complex emotions.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD]; [STAT.ML]Statistics [stat]/Machine Learning [stat.ML]; deep learning system; emergency call center; real life; recurrent neural network; speech emotion recognition; temporal neural networks
|
|
URL: https://hal.archives-ouvertes.fr/hal-03405970/document
https://hal.archives-ouvertes.fr/hal-03405970/file/main.pdf
https://hal.archives-ouvertes.fr/hal-03405970
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Corpus of Children Voices for Mid-level Markers and Affect Bursts Analysis
|
|
|
|
In: Language Ressource and Evaluation Conference (LREC) ; https://hal.archives-ouvertes.fr/hal-01768827 ; Language Ressource and Evaluation Conference (LREC), 2012, Istanbul, Turkey (2012)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Acoustic measures characterizing anger across corpora collected in artificial or natural context
|
|
|
|
In: Speech Prosody ; https://hal.archives-ouvertes.fr/hal-01768783 ; Speech Prosody, 2010, Chicago, United States (2010)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Whodunnit - Searching for the Most Important Feature Types Signalling Emotion-Related User States in Speech
|
|
|
|
In: ISSN: 0885-2308 ; EISSN: 1095-8363 ; Computer Speech and Language ; https://hal.archives-ouvertes.fr/hal-00661911 ; Computer Speech and Language, Elsevier, 2010, 25 (1), pp.4. ⟨10.1016/j.csl.2009.12.003⟩ (2010)
|
|
BASE
|
|
Show details
|
|
|
|
|
