Exploring Gender-Specific Speech Patterns in Automatic Suicide Risk Assessment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929421810663424 |
|---|---|
| author | Gerczuk, Maurice Amiriparian, Shahin Lutz, Justina Strube, Wolfgang Papazova, Irina Hasan, Alkomiet Schuller, Björn W. |
| author_facet | Gerczuk, Maurice Amiriparian, Shahin Lutz, Justina Strube, Wolfgang Papazova, Irina Hasan, Alkomiet Schuller, Björn W. |
| contents | In emergency medicine, timely intervention for patients at risk of suicide is often hindered by delayed access to specialised psychiatric care. To bridge this gap, we introduce a speech-based approach for automatic suicide risk assessment. Our study involves a novel dataset comprising speech recordings of 20 patients who read neutral texts. We extract four speech representations encompassing interpretable and deep features. Further, we explore the impact of gender-based modelling and phrase-level normalisation. By applying gender-exclusive modelling, features extracted from an emotion fine-tuned wav2vec2.0 model can be utilised to discriminate high- from low- suicide risk with a balanced accuracy of 81%. Finally, our analysis reveals a discrepancy in the relationship of speech characteristics and suicide risk between female and male subjects. For men in our dataset, suicide risk increases together with agitation while voice characteristics of female subjects point the other way. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11012 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Gender-Specific Speech Patterns in Automatic Suicide Risk Assessment Gerczuk, Maurice Amiriparian, Shahin Lutz, Justina Strube, Wolfgang Papazova, Irina Hasan, Alkomiet Schuller, Björn W. Computation and Language Machine Learning Sound Audio and Speech Processing 68T10 J.3 In emergency medicine, timely intervention for patients at risk of suicide is often hindered by delayed access to specialised psychiatric care. To bridge this gap, we introduce a speech-based approach for automatic suicide risk assessment. Our study involves a novel dataset comprising speech recordings of 20 patients who read neutral texts. We extract four speech representations encompassing interpretable and deep features. Further, we explore the impact of gender-based modelling and phrase-level normalisation. By applying gender-exclusive modelling, features extracted from an emotion fine-tuned wav2vec2.0 model can be utilised to discriminate high- from low- suicide risk with a balanced accuracy of 81%. Finally, our analysis reveals a discrepancy in the relationship of speech characteristics and suicide risk between female and male subjects. For men in our dataset, suicide risk increases together with agitation while voice characteristics of female subjects point the other way. |
| title | Exploring Gender-Specific Speech Patterns in Automatic Suicide Risk Assessment |
| topic | Computation and Language Machine Learning Sound Audio and Speech Processing 68T10 J.3 |
| url | https://arxiv.org/abs/2407.11012 |