Filters








360 Hits in 5.6 sec

Glottal Source Features for Automatic Speech-Based Depression Assessment

Olympia Simantiraki, Paulos Charonyktakis, Anastasia Pampouchidou, Manolis Tsiknakis, Martin Cooke
2017 Interspeech 2017   unpublished
Our findings indicate that Phase Distortion Deviation is a promising audio-only feature for automated detection and assessment of depressed speech.  ...  The current study explores categorical assessment of depression using audio features alone.  ...  Maria Koutsogiannaki for their valuable support. Anastasia Pampouchidou was funded by the "Maria Zaousi" scholarship from the Greek State Scholarships Foundation (I.K.Y).  ... 
doi:10.21437/interspeech.2017-1251 fatcat:rhqk4o2ap5e3rheizlf4akfuqa

Introduction to the Issue on Automatic Assessment of Health Disorders Based on Voice, Speech, and Language Processing

Juan I. Godino-Llorente, Douglas O'Shaughnessy, Tan Lee, Najim Dehak, Claudia Manfredi
2020 IEEE Journal on Selected Topics in Signal Processing  
Huang et al., in"Natural Language Processing Methods for Acoustic and Landmark Event-based Features in Speech-based Depression Detection," propose a framework for analyzing speech as a sequence of acoustic  ...  Glottal source features are extracted using glottal flows estimated with the quasi-closed phase (QCP) glottal inverse filtering method, using approximate glottal source signals computed with the zero frequency  ...  His recent research interests include automatic assessment of voice disorder, speech disorder and language impairment, analysis of child and elderly speech, and speech under pressure.  ... 
doi:10.1109/jstsp.2020.2978566 fatcat:32x76k4fnfhpbcpixz365muapm

Learning Voice Source Related Information for Depression Detection

S. Pavankumar Dubagunta, Bogdan Vlasenko, Mathew Magimai.-Doss
2019 ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
voice source related information for depression detection.  ...  In this paper, by exploiting the abilities of CNNs to learn task-relevant information from the input raw signals, we investigate several methods to model voice source related information for depression  ...  Following these studies, various voice source related features such as jitter, shimmer and glottal flow characterisation have been proposed as speech-based biomarkers for depression detection [18, 19]  ... 
doi:10.1109/icassp.2019.8683498 dblp:conf/icassp/DubaguntaVM19 fatcat:c574s66e5jejlc2szzwmjzm2pm

Glottal source processing: From analysis to applications

2014 Computer Speech and Language  
This paper gives a comprehensive overview of techniques for glottal source processing.  ...  Nonetheless, the major source of excitation, namely the glottal flow, is expected to convey useful complementary information.  ...  Features describing the glottal behaviour are therefore of great interest for the automatic audio-based detection of voice pathologies.  ... 
doi:10.1016/j.csl.2014.05.003 fatcat:ekopemusjvc5poddvzn3npsmym

Glottal source processing: From analysis to applications

Thomas Drugman, Paavo Alku, Abeer Alwan, Bayya Yegnanarayana
2014 Computer Speech and Language  
This paper gives a comprehensive overview of techniques for glottal source processing.  ...  Nonetheless, the major source of excitation, namely the glottal flow, is expected to convey useful complementary information.  ...  Features describing the glottal behaviour are therefore of great interest for the automatic audio-based detection of voice pathologies.  ... 
doi:10.1016/j.csl.2014.03.003 fatcat:a5yqvs364nep5eb3nws27yteoa

A review of depression and suicide risk assessment using speech analysis

Nicholas Cummins, Stefan Scherer, Jarek Krajewski, Sebastian Schnieder, Julien Epps, Thomas F. Quatieri
2015 Speech Communication  
This paper is the first review into the automatic analysis of speech for use as an objective predictor of depression and suicidality.  ...  This review starts by building the case for speech to be considered a key objective marker for both conditions; reviewing current diagnostic and assessment methods for depression and suicidality including  ...  Presence of depression A wide range of features have been trialled for automatic depressed speech classification.  ... 
doi:10.1016/j.specom.2015.03.004 fatcat:mjnho326mjbvbdengcp4lhs5xi

Audiovisual behavior descriptors for depression assessment

Stefan Scherer, Giota Stratou, Louis-Philippe Morency
2013 Proceedings of the 15th ACM on International conference on multimodal interaction - ICMI '13  
Based on a standard self-assessment depression scale we investigate the statistical discriminative strength of the audiovisual features on a depression/no-depression basis.  ...  We further correlate the behavior descriptors with the assessed depression severity and find considerable correlation.  ...  The analysis involved glottal flow features as well as prosodic features for the discrimination of depressed read speech of 15 male and 18 female speakers.  ... 
doi:10.1145/2522848.2522886 dblp:conf/icmi/SchererSM13 fatcat:vqfgypjovzbofmxnnwhjzaqfqi

Assessment of disordered voices based on an optimized glottal source model

Mounir BOUDJERDA, Abdellah KACHA
2017 Turkish Journal of Electrical Engineering and Computer Sciences  
In this paper, a method for the assessment of disordered voices is proposed.  ...  A feature named mean opening quotient (MOQ) obtained from the glottal source estimation is used as an acoustic cue to summarize the degree of severity of the voice disorder.  ...  The proposed method was tested on a corpus of natural speech including vowel [a] uttered by 251 speakers (normophonic and dysphonic).  ... 
doi:10.3906/elk-1608-324 fatcat:oxgkn3fc5rewzibakiyetfxcze

Dyadic Behavior Analysis in Depression Severity Assessment Interviews

Stefan Scherer, Zakia Hammal, Ying Yang, Louis-Philippe Morency, Jeffrey F. Cohn
2014 Proceedings of the 16th International Conference on Multimodal Interaction - ICMI '14  
Acoustic features for participants varied between men and women as expected, and failed to vary with depression severity for participants.  ...  Participants were interviewed for depression severity on up to four occasions over a 21 week period using the Hamilton Rating Scale for Depression (HRSD), which is a criterion measure for depression severity  ...  Normalized Amplitude Quotient (NAQ) The normalized amplitude quotient (NAQ) feature is derived from the glottal source signal estimated by iterative adaptive inverse filtering (IAIF, [3] ).  ... 
doi:10.1145/2663204.2663238 pmid:28345076 pmcid:PMC5365085 dblp:conf/icmi/SchererHYMC14 fatcat:i2clhtgvvvcqfbdgj5q6fwwmcy

Investigating the speech characteristics of suicidal adolescents

Stefan Scherer, John Pestian, Louis-Philippe Morency
2013 2013 IEEE International Conference on Acoustics, Speech and Signal Processing  
The work shows promising results in a speakerindependent classification experiment based on only a dozen speech features.  ...  Based on this limited dataset, we reveal statistically significant differences in the speech patterns of suicidal adolescents within the investigated interview corpus.  ...  The study in [4] involved the analysis of glottal flow features as well as prosodic features for the discrimination of depressed read speech of 15 male (nine controls and six depressed subjects, ages  ... 
doi:10.1109/icassp.2013.6637740 dblp:conf/icassp/SchererPM13 fatcat:jsjfxu5cynd5rfs524md3zjsba

Glottal Source Processing: from Analysis to Applications [article]

Thomas Drugman, Paavo Alku, Abeer Alwan, Bayya Yegnanarayana
2019 arXiv   pre-print
This review gives a general overview of techniques which have been designed for glottal source processing.  ...  Unfortunately, glottal analysis from speech recordings requires specific and more complex processing operations, which explains why it has been generally avoided.  ...  Features describing the glottal behaviour are therefore of great interest for the automatic audio-based detection of voice pathologies.  ... 
arXiv:1912.12604v1 fatcat:vcamvpic2najba2j6ksmvu33ny

Detection of Clinical Depression in Adolescents' Speech During Family Interactions

Lu-Shih Alex Low, M C Maddage, M Lech, L B Sheeber, N B Allen
2011 IEEE Transactions on Biomedical Engineering  
The TEO-based features clearly outperformed all other features and feature combinations, providing classification accuracy ranging between 81%-87% for males and 72%-79% for females.  ...  The properties of acoustic speech have previously been investigated as possible cues for depression in adults.  ...  Loizou, and the reviewers for their valuable feedback and suggestions.  ... 
doi:10.1109/tbme.2010.2091640 pmid:21075715 pmcid:PMC3652557 fatcat:7c5hxc5wtnfazmlpv7doal5uee

A Cross-modal Review of Indicators for Depression Detection Systems

Michelle Morales, Stefan Scherer, Rivka Levitan
2017 Proceedings of the Fourth Workshop on Computational Linguistics and Clinical Psychology –- From Linguistic Signal to Clinical Reality  
Automatic detection of depression has attracted increasing attention from researchers in psychology, computer science, linguistics, and related disciplines.  ...  As a result, promising depression detection systems have been reported.  ...  In addition, Morales and Levitan investigated using an automatic speech recognition system (ASR) to automatically transcribe speech and found that text-based features generated from ASR transcripts were  ... 
doi:10.18653/v1/w17-3101 dblp:conf/acl-clpsych/MoralesSL17 fatcat:ern3d56epraobnmryo5f2br3e4

Effectiveness of Voice Quality Features in Detecting Depression

Amber Afshan, Jinxi Guo, Soo Jin Park, Vijay Ravi, Jonathan Flint, Abeer Alwan
2018 Interspeech 2018  
Automatic assessment of depression from speech signals is affected by variabilities in acoustic content and speakers. In this study, we focused on addressing these variabilities.  ...  In order to capture various aspects of speech signals, we used voice quality features in addition to conventional cepstral features.  ...  Voice Quality Features (VQual) Based on extensive studies on the patterns of variability across speakers in source spectral shapes and glottal pulse shapes [34] , a spectral model to represent the voice  ... 
doi:10.21437/interspeech.2018-1399 dblp:conf/interspeech/AfshanGPRFA18 fatcat:vbvqwgdf3fh75f7naluojux4c4

Objective Methods for Reliable Detection of Concealed Depression

Cynthia Solomon, Michel F. Valstar, Richard K. Morriss, John Crowe
2015 Frontiers in ICT  
For more information, please contact eprints@nottingham.ac.uk ICT ORIGINAL RESEARCH ARTICLE Recent research has shown that it is possible to automatically detect clinical depression from audio-visual recordings  ...  2015) Objective methods for reliable detection of concealed depression. Frontiers in ICT, 2 . 5/1-5/16.  ...  Part of RM's work is funded by the National Institute of Healthcare Research Collaboration for Leadership in Applied Health Research and Care (NIHR CLAHRC) East Midlands.  ... 
doi:10.3389/fict.2015.00005 fatcat:6bfyzvvfuvhh7m3b5vbcweqi6m
« Previous Showing results 1 — 15 out of 360 results