Depression-level assessment from multi-lingual conversational speech data using acoustic and text features
Abstract Depression is a widespread mental health problem around the world with a significant burden on economies. Its early diagnosis and treatment are critical to reduce the costs and even save lives. One key aspect to achieve that goal is to use technology and monitor depression remotely and rela...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-11-01
|
| Series: | EURASIP Journal on Audio, Speech, and Music Processing |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13636-020-00182-4 |
| _version_ | 1818437098529619968 |
|---|---|
| author | Cenk Demiroglu Aslı Beşirli Yasin Ozkanca Selime Çelik |
| author_facet | Cenk Demiroglu Aslı Beşirli Yasin Ozkanca Selime Çelik |
| author_sort | Cenk Demiroglu |
| collection | DOAJ |
| description | Abstract Depression is a widespread mental health problem around the world with a significant burden on economies. Its early diagnosis and treatment are critical to reduce the costs and even save lives. One key aspect to achieve that goal is to use technology and monitor depression remotely and relatively inexpensively using automated agents. There has been numerous efforts to automatically assess depression levels using audiovisual features as well as text-analysis of conversational speech transcriptions. However, difficulty in data collection and the limited amounts of data available for research present challenges that are hampering the success of the algorithms. One of the two novel contributions in this paper is to exploit databases from multiple languages for acoustic feature selection. Since a large number of features can be extracted from speech, given the small amounts of training data available, effective data selection is critical for success. Our proposed multi-lingual method was effective at selecting better features than the baseline algorithms, which significantly improved the depression assessment accuracy. The second contribution of the paper is to extract text-based features for depression assessment and use a novel algorithm to fuse the text- and speech-based classifiers which further boosted the performance. |
| first_indexed | 2024-12-14T17:19:16Z |
| format | Article |
| id | doaj.art-75c967b5360c48c187c272646f87a856 |
| institution | Directory Open Access Journal |
| issn | 1687-4722 |
| language | English |
| last_indexed | 2024-12-14T17:19:16Z |
| publishDate | 2020-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Audio, Speech, and Music Processing |
| spelling | doaj.art-75c967b5360c48c187c272646f87a8562022-12-21T22:53:22ZengSpringerOpenEURASIP Journal on Audio, Speech, and Music Processing1687-47222020-11-012020111710.1186/s13636-020-00182-4Depression-level assessment from multi-lingual conversational speech data using acoustic and text featuresCenk Demiroglu0Aslı Beşirli1Yasin Ozkanca2Selime Çelik3Department of Electrical and Electronics Engineering, Ozyegin UniversityUniversity of Health Sciences Turkey, Şişli Hamidiye Etfal Training and Research Hospital, Department of PsychiatryDepartment of Electrical and Electronics Engineering, Ozyegin UniversityUniversity of Health Sciences Turkey, Şişli Hamidiye Etfal Training and Research Hospital, Department of PsychiatryAbstract Depression is a widespread mental health problem around the world with a significant burden on economies. Its early diagnosis and treatment are critical to reduce the costs and even save lives. One key aspect to achieve that goal is to use technology and monitor depression remotely and relatively inexpensively using automated agents. There has been numerous efforts to automatically assess depression levels using audiovisual features as well as text-analysis of conversational speech transcriptions. However, difficulty in data collection and the limited amounts of data available for research present challenges that are hampering the success of the algorithms. One of the two novel contributions in this paper is to exploit databases from multiple languages for acoustic feature selection. Since a large number of features can be extracted from speech, given the small amounts of training data available, effective data selection is critical for success. Our proposed multi-lingual method was effective at selecting better features than the baseline algorithms, which significantly improved the depression assessment accuracy. The second contribution of the paper is to extract text-based features for depression assessment and use a novel algorithm to fuse the text- and speech-based classifiers which further boosted the performance.http://link.springer.com/article/10.1186/s13636-020-00182-4Depression detectionAcoustic featuresFeature selection |
| spellingShingle | Cenk Demiroglu Aslı Beşirli Yasin Ozkanca Selime Çelik Depression-level assessment from multi-lingual conversational speech data using acoustic and text features EURASIP Journal on Audio, Speech, and Music Processing Depression detection Acoustic features Feature selection |
| title | Depression-level assessment from multi-lingual conversational speech data using acoustic and text features |
| title_full | Depression-level assessment from multi-lingual conversational speech data using acoustic and text features |
| title_fullStr | Depression-level assessment from multi-lingual conversational speech data using acoustic and text features |
| title_full_unstemmed | Depression-level assessment from multi-lingual conversational speech data using acoustic and text features |
| title_short | Depression-level assessment from multi-lingual conversational speech data using acoustic and text features |
| title_sort | depression level assessment from multi lingual conversational speech data using acoustic and text features |
| topic | Depression detection Acoustic features Feature selection |
| url | http://link.springer.com/article/10.1186/s13636-020-00182-4 |
| work_keys_str_mv | AT cenkdemiroglu depressionlevelassessmentfrommultilingualconversationalspeechdatausingacousticandtextfeatures AT aslıbesirli depressionlevelassessmentfrommultilingualconversationalspeechdatausingacousticandtextfeatures AT yasinozkanca depressionlevelassessmentfrommultilingualconversationalspeechdatausingacousticandtextfeatures AT selimecelik depressionlevelassessmentfrommultilingualconversationalspeechdatausingacousticandtextfeatures |