Assessing speaker independence on a speech-based depression level estimation system

López-Otero, Paula; Docío-Fernández, Laura; Garcı́a-Mateo, Carmen

doi:10.1016/j.patrec.2015.05.017

Cited by 22 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Paula et al in [25] perform experiments using MFCCs, Shifted-Delta-Cepstra (SDC), Rasta Perceptual Linear Prediction Coefficients (PLP), and spectral and prosodic features as input to an i-vector system with feature concatenation for estimating depression level. Further, experiments in a speaker independent setup are shown in [26]. A multimodal setup using video features as well with MFCC based i-vectors is described in [27].…”

Section: Related Work On Voice Quality and I-vectorsmentioning

confidence: 99%

Effectiveness of Voice Quality Features in Detecting Depression

et al. 2018

View full text Add to dashboard Cite

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. We used a database comprised of recordings of interviews from a large number of female speakers: 735 individuals suffering from depressive (dysthymia and major depression) and anxiety disorders (generalized anxiety disorder, panic disorder with or without agoraphobia) and 953 healthy individuals. Leveraging this unique and extensive database, we built an i-vector framework. In order to capture various aspects of speech signals, we used voice quality features in addition to conventional cepstral features. The features (F0, F1, F2, F3, H1-H2, H2-H4, H4-H2k, A1, A2, A3, and CPP) were inspired by a psychoacoustic model of voice quality [1]. An i-vector-based system using Mel Frequency Cepstral Coefficients (MFCCs) and another using voice quality features was developed. Voice quality features performed as well as MFCCs. A score-level fusion was then used to combine these two systems, resulting in a 6% relative improvement in accuracy in comparison with the i-vector system based on MFCCs alone. The system was robust even when the duration of the utterances was shortened to 10 seconds.

show abstract

Section: Related Work On Voice Quality and I-vectorsmentioning

confidence: 99%

Effectiveness of Voice Quality Features in Detecting Depression

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The winning entry for the subchallenge [11] exploited changes in correlations across formant frequencies and channels of the delta-mel-cepstrum using a Gaussian mixture model (GMM). Subsequent approaches using AVEC-2013 include Cummins et al [12], who employed acoustic volume analysis combined with GMMs, Scherer et al [13], who explore reduced vowel space as an indicator of distress, and the iVector-based approach of Lopez-Ottero et al [14] applied to four depression severity classes.…”

Section: Related Workmentioning

confidence: 99%

“…Labels of the testing partition were withheld for challenge purposes, so in the present study only the 200 recordings from the development and train sets were used. The dataset was annotated with a single label per recording, corresponding to speakers' scores on BDI-II, which according to its standardized cutoffs can be interpreted as minimal depression for a score of [0-13], mild [14][15][16][17][18][19], moderate [20][21][22][23][24][25][26][27][28]…”

Section: Datasetsmentioning

confidence: 99%

Glottal Source Features for Automatic Speech-Based Depression Assessment

et al. 2017

View full text Add to dashboard Cite

Depression is one of the most prominent mental disorders, with an increasing rate that makes it the fourth cause of disability worldwide. The field of automated depression assessment has emerged to aid clinicians in the form of a decision support system. Such a system could assist as a pre-screening tool, or even for monitoring high risk populations. Related work most commonly involves multimodal approaches, typically combining audio and visual signals to identify depression presence and/or severity. The current study explores categorical assessment of depression using audio features alone. Specifically, since depression-related vocal characteristics impact the glottal source signal, we examine Phase Distortion Deviation which has previously been applied to the recognition of voice qualities such as hoarseness, breathiness and creakiness, some of which are thought to be features of depressed speech. The proposed method uses as features DCT-coefficients of the Phase Distortion Deviation for each frequency band. An automated machine learning tool, Just Add Data, is used to classify speech samples. The method is evaluated on a benchmark dataset (AVEC2014), in two conditions: read-speech and spontaneous-speech. Our findings indicate that Phase Distortion Deviation is a promising audio-only feature for automated detection and assessment of depressed speech.

show abstract

“…The depression level estimation system used for our research represents speech information using the i-vector paradigm [4,16,19]. The use of i-vectors for depression level estimation aims at tackling the variability arising from gender, age, channel, speaker or message in the different recordings.…”

Section: Automatic Depression Detectionmentioning

confidence: 99%

“…The assessed speaker de-identification approaches are suitable for these experiments since they can be straightforwardly applied to any speaker without having to train transformation functions between the input and target speakers [10,11]. Regarding the estimation of depression severity, an approach based on acoustic characteristics and i-vector representation combined with support vector regression is chosen [19] due to the characteristics of AVEC 2014 data and its acceptable results in this experimental framework.…”

Section: Introductionmentioning

confidence: 99%

Influence of speaker de‐identification in depression detection

López-Otero

Magariños

Docío-Fernández

et al. 2017

IET signal process.

View full text Add to dashboard Cite

Depression is a common mental disorder that is usually addressed by outpatient treatments that favour patients' inclusion in the society. This raises the need for tools to remotely monitor the emotional state of the patients, which can be carried out via telephone or the Internet using speech processing approaches. However, these strategies lead to privacy concerns caused by the transmission of the patients' speech and its subsequent storage in servers. The use of speech deidentification to protect the privacy of these patients seems straightforward, but the influence of this procedure in the manifestation of the disease in the patients' speech has not been addressed yet. Hence, this study evaluates the performance of an automatic depression level estimation system when dealing with original and de-identified speech, in order to analyse the influence of the de-identification procedure in the detection of depression. Two de-identification approaches based on voice transformation via frequency warping and amplitude scaling are assessed, which can be applied to any speaker without additional training. Experiments carried out in the framework of the audio/visual emotion challenge 2014 show that the proposed de-identification approaches achieve promising de-identification results at the expense of a slight degradation of depression detection.

show abstract

Assessing speaker independence on a speech-based depression level estimation system

Cited by 22 publications

References 25 publications

Effectiveness of Voice Quality Features in Detecting Depression

Effectiveness of Voice Quality Features in Detecting Depression

Glottal Source Features for Automatic Speech-Based Depression Assessment

Influence of speaker de‐identification in depression detection

Contact Info

Product

Resources

About