short-paper

Autoencoder Based on Cepstrum Separation to Detect Depression from Speech

Authors:

Yuanhua Zhang,

Weiping Hu,

Qing WuAuthors Info & Claims

ICITEE '20: Proceedings of the 3rd International Conference on Information Technologies and Electrical Engineering

Pages 508 - 510

https://doi.org/10.1145/3452940.3453038

Published: 17 May 2021 Publication History

Get Access

Abstract

Depression has become a common mental disorder that plagues more and more people. This paper uses speech signals to study a method for predicting the degree of depression and help clinicians judge the degree of depression in patients. In this paper, a autoencoder model based on Bidirectional Gated Recurrent Unit (BiGRU) is proposed to extract deep speech features, with the original speech as the network input, the signal after the cepstrum separation as the training target. In this model, we take the original speech as the input of the network, and the homomorphic speech as the training target of the model. The long-term deep features extracted by the model and the short-time shallow features extracted by the Opensmile toolkit were sent into Random Forest (RF) respectively, and finally the Support Vector Regression (SVR) was used for decision fusion recognition. In this paper, experiments are conducted on the DAIC-WOZ data set, and the Root Mean Square Error (RMSE) is 5.68 and the Mean Absolute Error (MAE) is 4.64.

References

[1]

Kurniawan H, Maslov A V, Pechenizkiy M. Stress detection from speech and galvanic skin response signals[C]//Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems. IEEE, 2013: 209--214.

Google Scholar

[2]

Huilian L, Weiping H, Yan W. Speech Emotion Recognition Based on BLSTM and CNN Feature Fusion[C]//Proceedings of the 2020 4th International Conference on Digital Signal Processing. 2020: 169--172.

Google Scholar

[3]

John W. Kim, Rif A. Saurous. 2018. Emotion Recognition from Human Speech Using Temporal Information and Deep Learning. In Proceedings of the Interspeech 2018. 2018-1132.

Google Scholar

[4]

Zhao J, Su W, Jia J, et al. Research on depression detection algorithm combine acoustic rhythm with sparse face recognition[J]. Cluster Computing, 2019: 1--12.

Google Scholar

[5]

Yang L, Jiang D, Xia X, et al. Multimodal measurement of depression using deep learning models[C]//Proceedings of the 7th Annual Workshop on Audio/Visual Emotion Challenge.

Google Scholar

[6]

Senoussaoui M, Cardinal P, Koerich A L. Bag-of-Audio-Words based on Autoencoder Codebook for Continuous Emotion Prediction[J]. arXiv preprint arXiv:1907.04928, 2019.

Google Scholar

[7]

Dinkel H, Zhang P, Wu M, et al. Depa: Self-supervised audio embedding for depression detection[J]. arXiv preprint arXiv:1910.13028, 2019.

Google Scholar

[8]

A. Bouzid and N. Ellouze, "Glottal opening instant detection from speech signal, " 2004 12th European Signal Processing Conference, Vienna, 2004, pp. 729--732.

Google Scholar

[9]

Oppenheim A V. Speech analysis-synthesis system based on homomorphic filtering[J]. The Journal of the Acoustical Society of America, 1969, 45(2): 458--465.

Crossref

Google Scholar

[10]

Ringeval F, Schuller B, Valstar M, et al. Avec 2017: Real-life depression, and affect recognition workshop and challenge[C]//Proceedings of the 7th Annual Workshop on Audio/Visual Emotion Challenge. 2017: 3--9.

Google Scholar

[11]

Schuller B, Steidl S, Batliner A. The interspeech 2009 emotion challenge[C]//Tenth Annual Conference of the International Speech Communication Association. 2009.

Google Scholar

Cited By

View all

Lu JLiu BLian ZCai CTao JZhao Z(2022)Prediction of Depression Severity Based on Transformer Encoder and CNN Model2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)10.1109/ISCSLP57327.2022.10038064(339-343)Online publication date: 11-Dec-2022
https://doi.org/10.1109/ISCSLP57327.2022.10038064
He LNiu MTiwari PMarttinen PSu RJiang JGuo CWang HDing SWang ZPan XDang W(2022)Deep learning for depression recognition with audiovisual cuesInformation Fusion10.1016/j.inffus.2021.10.01280:C(56-86)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.1016/j.inffus.2021.10.012
Ditthapron AAgu ELammert A(2021)Learning from Limited Data for Speech-based Traumatic Brain Injury (TBI) Detection2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)10.1109/ICMLA52953.2021.00239(1482-1486)Online publication date: Dec-2021
https://doi.org/10.1109/ICMLA52953.2021.00239

Index Terms

Autoencoder Based on Cepstrum Separation to Detect Depression from Speech

Index terms have been assigned to the content through auto-classification.

Recommendations

Acoustic Feature Comparison of MFCC and CZT-Based Cepstrum for Speech Recognition
ICNC '09: Proceedings of the 2009 Fifth International Conference on Natural Computation - Volume 01

The speech cepstral features are important parameter in Automatic Speech Recognition (ASR), which symbolizes the property of human auditory system (HAS). The Mel-Frequency Cepstral Coefficients (MFCC) are the most widely used features in speech ...
Acoustic feature comparison of MFCC and CZT-based cepstrum for speech recognition
ICNC'09: Proceedings of the 5th international conference on Natural computation

The speech cepstral features are important parameter in Automatic Speech Recognition (ASR), which symbolizes the property of human auditory system (HAS). The Mel-Frequency Cepstral Coefficients (MFCC) are the most widely used features in speech ...
Whispered Speech Recognition Using Deep Denoising Autoencoder and Inverse Filtering

Due to the profound differences between acoustic characteristics of neutral and whispered speech, the performance of traditional automatic speech recognition ASR systems trained on neutral speech degrades significantly when whisper is applied. In order ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

ICITEE '20: Proceedings of the 3rd International Conference on Information Technologies and Electrical Engineering

December 2020

687 pages

ISBN:9781450388665

DOI:10.1145/3452940

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 May 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper
Research
Refereed limited

Funding Sources

National Natural Science Foundation of China

Conference

ICITEE2020

ICITEE2020: The 3rd International Conference on Information Technologies and Electrical Engineering

December 3 - 5, 2020

Hunan, Changde City, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
98
Total Downloads

Downloads (Last 12 months)21
Downloads (Last 6 weeks)1

Reflects downloads up to 21 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Lu JLiu BLian ZCai CTao JZhao Z(2022)Prediction of Depression Severity Based on Transformer Encoder and CNN Model2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)10.1109/ISCSLP57327.2022.10038064(339-343)Online publication date: 11-Dec-2022
https://doi.org/10.1109/ISCSLP57327.2022.10038064
He LNiu MTiwari PMarttinen PSu RJiang JGuo CWang HDing SWang ZPan XDang W(2022)Deep learning for depression recognition with audiovisual cuesInformation Fusion10.1016/j.inffus.2021.10.01280:C(56-86)Online publication date: 1-Apr-2022
https://dl.acm.org/doi/10.1016/j.inffus.2021.10.012
Ditthapron AAgu ELammert A(2021)Learning from Limited Data for Speech-based Traumatic Brain Injury (TBI) Detection2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)10.1109/ICMLA52953.2021.00239(1482-1486)Online publication date: Dec-2021
https://doi.org/10.1109/ICMLA52953.2021.00239

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Acoustic Feature Comparison of MFCC and CZT-Based Cepstrum for Speech Recognition

Acoustic feature comparison of MFCC and CZT-based cepstrum for speech recognition

Whispered Speech Recognition Using Deep Denoising Autoencoder and Inverse Filtering