An End-to-End Deep Learning Framework with Speech Emotion Recognition of Atypical Individuals

被引：0

作者：

Tang, Dengke ^{[2
]}

Zeng, Junlin ^{[2
]}

Li, Ming ^{[1
]}

机构：

[1] Duke Kunshan Univ, Data Sci Res Ctr, Kunshan, Peoples R China

[2] Sun Yat Sen Univ, Sch Data & Comp Sci, Guangzhou, Guangdong, Peoples R China

来源：

19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES | 2018年

基金：

中国国家自然科学基金;

关键词：

computational paralinguistics; atypical affect; end-to-end framework;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The goal of the ongoing ComParE 2018 Atypical Affect sub challenge is to recognize the emotional states of atypical individuals. In this work, we present three modeling methods under the end-to-end learning framework, namely CNN combined with extended features, CNN+RNN and ResNet, respectively. Furthermore, we investigate multiple data augmentation, balancing and sampling methods to further enhance the system performance. The experimental results show that data balancing and augmentation increase the unweighted accuracy (UAR) by 10% absolutely. After score level fusion, our proposed system achieves 48.8% UAR on the develop dataset.

引用

页码：162 / 166

页数：5

共 50 条

[1] END-TO-END SPEECH EMOTION RECOGNITION USING DEEP NEURAL NETWORKS
Tzirakis, Panagiotis
Zhang, Jiehao
Schuller, Bjoern W.
[J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5089 - 5093
[2] AN END-TO-END MULTITASK LEARNING MODEL TO IMPROVE SPEECH EMOTION RECOGNITION
Fu, Changzeng
Liu, Chaoran
Ishi, Carlos Toshinori
Ishiguro, Hiroshi
[J]. 28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 351 - 355
[3] Arabic speech recognition using end-to-end deep learning
Alsayadi, Hamzah A.
Abdelhamid, Abdelaziz A.
Hegazy, Islam
Fayed, Zaki T.
[J]. IET SIGNAL PROCESSING, 2021, 15 (08) : 521 - 534
[4] End-to-End Automatic Speech Recognition with Deep Mutual Learning
Masumura, Ryo
Ihori, Mana
Takashima, Akihiko
Tanaka, Tomohiro
Ashihara, Takanori
[J]. 2020 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2020, : 632 - 637
[5] An End-to-End Deep Learning Framework for Wideband Signal Recognition
Vagollari, Adela
Hirschbeck, Martin
Gerstacker, Wolfgang
[J]. IEEE ACCESS, 2023, 11 : 52899 - 52922
[6] End-to-End Deep Learning Speech Recognition Model for Silent Speech Challenge
Kimura, Naoki
Su, Zixiong
Saeki, Takaaki
[J]. INTERSPEECH 2020, 2020, : 1025 - 1026
[7] End-to-End Speech Emotion Recognition With Gender Information
Sun, Ting-Wei
[J]. IEEE ACCESS, 2020, 8 : 152423 - 152438
[8] A Bayesian Deep Learning Framework for End-To-End Prediction of Emotion From Heartbeat
Harper, Ross
Southern, Joshua
[J]. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2022, 13 (02) : 985 - 991
[9] End-to-End Speech Emotion Recognition Based on Neural Network
Zhu, Bing
Zhou, Wenkai
Wang, Yutian
Wang, Hui
Cai, Juan Juan
[J]. 2017 17TH IEEE INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY (ICCT 2017), 2017, : 1634 - 1638
[10] Speech Representation Learning for Emotion Recognition Using End-to-End ASR with Factorized Adaptation
Yeh, Sung-Lin
Lin, Yun-Shao
Lee, Chi-Chun
[J]. INTERSPEECH 2020, 2020, : 536 - 540

← 1 2 3 4 5 →