Dataset Information

Using speech recognition technology to investigate the association between timing-related speech features and depression severity.

ABSTRACT: BACKGROUND:There are no reliable and validated objective biomarkers for the assessment of depression severity. We aimed to investigate the association between depression severity and timing-related speech features using speech recognition technology. METHOD:Patients with major depressive disorder (MDD), those with bipolar disorder (BP), and healthy controls (HC) were asked to engage in a non-structured interview with research psychologists. Using automated speech recognition technology, we measured three timing-related speech features: speech rate, pause time, and response time. The severity of depression was assessed using the Hamilton Depression Rating Scale 17-item version (HAMD-17). We conducted the current study to answer the following questions: 1) Are there differences in speech features among MDD, BP, and HC? 2) Do speech features correlate with depression severity? 3) Do changes in speech features correlate with within-subject changes in depression severity? RESULTS:We collected 1058 data sets from 241 individuals for the study (97 MDD, 68 BP, and 76 HC). There were significant differences in speech features among groups; depressed patients showed slower speech rate, longer pause time, and longer response time than HC. All timing-related speech features showed significant associations with HAMD-17 total scores. Longitudinal changes in speech rate correlated with changes in HAMD-17 total scores. CONCLUSIONS:Depressed individuals showed longer response time, longer pause time, and slower speech rate than healthy individuals, all of which were suggestive of psychomotor retardation. Our study suggests that speech features could be used as objective biomarkers for the assessment of depression severity.

SUBMITTER: Yamamoto M

PROVIDER: S-EPMC7485753 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using speech recognition technology to investigate the association between timing-related speech features and depression severity.

Yamamoto Mao M Takamiya Akihiro A Sawada Kyosuke K Yoshimura Michitaka M Kitazawa Momoko M Liang Kuo-Ching KC Fujita Takanori T Mimura Masaru M Kishimoto Taishiro T

PloS one 20200911 9

<h4>Background</h4>There are no reliable and validated objective biomarkers for the assessment of depression severity. We aimed to investigate the association between depression severity and timing-related speech features using speech recognition technology.<h4>Method</h4>Patients with major depressive disorder (MDD), those with bipolar disorder (BP), and healthy controls (HC) were asked to engage in a non-structured interview with research psychologists. Using automated speech recognition techn ...[more]

PMID: 32915846

Similar Datasets

Project description:BackgroundSeveral studies have investigated the acoustic effects of diagnosed anxiety and depression. Anxiety and depression are not characteristics of the typical aging process, but minimal or mild symptoms can appear and evolve with age. However, the knowledge about the association between speech and anxiety or depression is scarce for minimal/mild symptoms, typical of healthy aging. As longevity and aging are still a new phenomenon worldwide, posing also several clinical challenges, it is important to improve our understanding of non-severe mood symptoms' impact on acoustic features across lifetime. The purpose of this study was to determine if variations in acoustic measures of voice are associated with non-severe anxiety or depression symptoms in adult population across lifetime.MethodsTwo different speech tasks (reading vowels in disyllabic words and describing a picture) were produced by 112 individuals aged 35-97. To assess anxiety and depression symptoms, the Hospital Anxiety Depression Scale (HADS) was used. The association between the segmental and suprasegmental acoustic parameters and HADS scores were analyzed using the linear multiple regression technique.ResultsThe number of participants with presence of anxiety or depression symptoms is low (>7: 26.8% and 10.7%, respectively) and non-severe (HADS-A: 5.4 ± 2.9 and HADS-D: 4.2 ± 2.7, respectively). Adults with higher anxiety symptoms did not present significant relationships associated with the acoustic parameters studied. Adults with increased depressive symptoms presented higher vowel duration, longer total pause duration and short total speech duration. Finally, age presented a positive and significant effect only for depressive symptoms, showing that older participants tend to have more depressive symptoms.ConclusionsNon-severe depression symptoms can be related to some acoustic parameters and age. Depression symptoms can be explained by acoustic parameters even among individuals without severe symptom levels.

Project description:BACKGROUND: Treacher Collins syndrome (TCS, OMIM 154500) is a rare congenital disorder of craniofacial development. Characteristic hypoplastic malformations of the ears, zygomatic arch, mandible and pharynx have been described in detail. However, reports on the impact of these malformations on speech are few. Exploring speech features and investigating if speech function is related to phenotypic severity are essential for optimizing follow-up and treatment. METHODS: Articulation, nasal resonance, voice and intelligibility were examined in 19 individuals (5-74 years, median 34 years) divided into three groups comprising children 5-10 years (n?=?4), adolescents 11-18 years (n?=?4) and adults 29 years and older (n?=?11). A speech composite score (0-6) was calculated to reflect the variability of speech deviations. TCS severity scores of phenotypic expression and total scores of Nordic Orofacial Test-Screening (NOT-S) measuring orofacial dysfunction were used in analyses of correlation with speech characteristics (speech composite scores). RESULTS: Children and adolescents presented with significantly higher speech composite scores (median 4, range 1-6) than adults (median 1, range 0-5). Nearly all children and adolescents (6/8) displayed speech deviations of articulation, nasal resonance and voice, while only three adults were identified with multiple speech aberrations. The variability of speech dysfunction in TCS was exhibited by individual combinations of speech deviations in 13/19 participants. The speech composite scores correlated with TCS severity scores and NOT-S total scores. Speech composite scores higher than 4 were associated with cleft palate. The percent of intelligible words in connected speech was significantly lower in children and adolescents (median 77%, range 31-99) than in adults (98%, range 93-100). Intelligibility of speech among the children was markedly inconsistent and clearly affecting the understandability. CONCLUSIONS: Multiple speech deviations were identified in children, adolescents and a subgroup of adults with TCS. Only children displayed markedly reduced intelligibility. Speech was significantly correlated with phenotypic severity of TCS and orofacial dysfunction. Follow-up and treatment of speech should still be focused on young patients, but some adults with TCS seem to require continuing speech and language pathology services.

Project description:ImportanceMultiple studies have evaluated associations between post-cochlear implant (CI) speech recognition outcomes and patient-related factors. Current literature often appears equivocal or contradictory, so little is known about the factors that contribute to successful speech recognition outcomes with CIs.ObjectiveTo use a meta-analysis to pool data from the extant literature and provide an objective summary of existing evidence on associations of patient-related factors and CI speech recognition outcomes.Data sourcesA literature search was performed using PubMed, Scopus, and CINAHL databases in January 2019 using the following search terms: cochlear implant or cochlear implants or cochlear implantation and speech recognition or word recognition or sentence recognition. Studies of postlingually deafened adult CI recipients that reported word or sentence recognition scores were included.Study selectionInclusion criteria were postlingual adult CI recipients 18 years or older with word or sentence recognition scores at minimum 6-month postimplantation. Studies that included patients undergoing revision or reimplantation surgery were excluded.Data extraction and synthesisFollowing the Preferred Reporting Items for Systemic Reviews and Meta-analyses (PRISMA) guidelines, 1809 unique articles underwent review by abstract, and 121 articles underwent full-text review, resulting in 13 articles of 1095 patients for a meta-analysis of correlations. Random-effects model was used when the heterogeneity test yielded a low P value (P < .05).Main outcomes and measuresThe planned primary outcome was the pooled correlation values between postimplant speech recognition scores and patient-related factors.ResultsOf the 1095 patients included from the 13 studies, the mean age at implantation ranged from 51.2 to 63.7 years and the mean duration of hearing loss ranged from 9.5 to 31.8 years; for the 825 patients for whom sex was reported, 421 (51.0%) were women. A weak negative correlation was observed between age at implantation and postimplant sentence recognition in quiet (r = -0.31 [95% CI, -0.41 to -0.20]). Other correlations between patient-related factors and postimplant word or sentence recognition were statistically significant, but all correlations were absent to negligible (r = 0.02-0.27).Conclusions and relevanceGiven that most associations were weak, negligible, or absent, patient-related factors often thought to affect CI speech recognition ability offer limited assistance in clinical decision-making in cochlear implantation. Additional research is needed to identify patient-related and other factors that predict CI outcomes, including speech recognition and other important variables related to success with CIs.

Project description:ImportanceThe association between major depressive disorder (MDD) and obesity may stem from shared immunometabolic mechanisms particularly evident in MDD with atypical features, characterized by increased appetite and/or weight (A/W) during an active episode.ObjectiveTo determine whether subgroups of patients with MDD stratified according to the A/W criterion had a different degree of genetic overlap with obesity-related traits (body mass index [BMI] and levels of C-reactive protein [CRP] and leptin).Design, setting, and patientsThis multicenter study assembled genome-wide genotypic and phenotypic measures from 14 data sets of the Psychiatric Genomics Consortium. Data sets were drawn from case-control, cohort, and population-based studies, including 26 628 participants with established psychiatric diagnoses and genome-wide genotype data. Data on BMI were available for 15 237 participants. Data were retrieved and analyzed from September 28, 2015, through May 20, 2017.Main outcomes and measuresLifetime DSM-IV MDD was diagnosed using structured diagnostic instruments. Patients with MDD were stratified into subgroups according to change in the DSM-IV A/W symptoms as decreased or increased.ResultsData included 11 837 participants with MDD and 14 791 control individuals, for a total of 26 628 participants (59.1% female and 40.9% male). Among participants with MDD, 5347 (45.2%) were classified in the decreased A/W and 1871 (15.8%) in the increased A/W subgroups. Common genetic variants explained approximately 10% of the heritability in the 2 subgroups. The increased A/W subgroup showed a strong and positive genetic correlation (SE) with BMI (0.53 [0.15]; P = 6.3 × 10-4), whereas the decreased A/W subgroup showed an inverse correlation (-0.28 [0.14]; P = .06). Furthermore, the decreased A/W subgroup had a higher polygenic risk for increased BMI (odds ratio [OR], 1.18; 95% CI, 1.12-1.25; P = 1.6 × 10-10) and levels of CRP (OR, 1.08; 95% CI, 1.02-1.13; P = 7.3 × 10-3) and leptin (OR, 1.09; 95% CI, 1.06-1.12; P = 1.7 × 10-3).Conclusions and relevanceThe phenotypic associations between atypical depressive symptoms and obesity-related traits may arise from shared pathophysiologic mechanisms in patients with MDD. Development of treatments effectively targeting immunometabolic dysregulations may benefit patients with depression and obesity, both syndromes with important disability.

Project description:BackgroundThe measurement and monitoring of generalized anxiety disorder requires frequent interaction with psychiatrists or psychologists. Access to mental health professionals is often difficult because of high costs or insufficient availability. The ability to assess generalized anxiety disorder passively and at frequent intervals could be a useful complement to conventional treatment and help with relapse monitoring. Prior work suggests that higher anxiety levels are associated with features of human speech. As such, monitoring speech using personal smartphones or other wearable devices may be a means to achieve passive anxiety monitoring.ObjectiveThis study aims to validate the association of previously suggested acoustic and linguistic features of speech with anxiety severity.MethodsA large number of participants (n=2000) were recruited and participated in a single web-based study session. Participants completed the Generalized Anxiety Disorder 7-item scale assessment and provided an impromptu speech sample in response to a modified version of the Trier Social Stress Test. Acoustic and linguistic speech features were a priori selected based on the existing speech and anxiety literature, along with related features. Associations between speech features and anxiety levels were assessed using age and personal income as covariates.ResultsWord count and speaking duration were negatively correlated with anxiety scores (r=-0.12; P<.001), indicating that participants with higher anxiety scores spoke less. Several acoustic features were also significantly (P<.05) associated with anxiety, including the mel-frequency cepstral coefficients, linear prediction cepstral coefficients, shimmer, fundamental frequency, and first formant. In contrast to previous literature, second and third formant, jitter, and zero crossing rate for the z score of the power spectral density acoustic features were not significantly associated with anxiety. Linguistic features, including negative-emotion words, were also associated with anxiety (r=0.10; P<.001). In addition, some linguistic relationships were sex dependent. For example, the count of words related to power was positively associated with anxiety in women (r=0.07; P=.03), whereas it was negatively associated with anxiety in men (r=-0.09; P=.01).ConclusionsBoth acoustic and linguistic speech measures are associated with anxiety scores. The amount of speech, acoustic quality of speech, and gender-specific linguistic characteristics of speech may be useful as part of a system to screen for anxiety, detect relapse, or monitor treatment.

Project description:In the real world, human speech recognition nearly always involves listening in background noise. The impact of such noise on speech signals and on intelligibility performance increases with the separation of the listener from the speaker. The present behavioral experiment provides an overview of the effects of such acoustic disturbances on speech perception in conditions approaching ecologically valid contexts. We analysed the intelligibility loss in spoken word lists with increasing listener-to-speaker distance in a typical low-level natural background noise. The noise was combined with the simple spherical amplitude attenuation due to distance, basically changing the signal-to-noise ratio (SNR). Therefore, our study draws attention to some of the most basic environmental constraints that have pervaded spoken communication throughout human history. We evaluated the ability of native French participants to recognize French monosyllabic words (spoken at 65.3 dB(A), reference at 1 meter) at distances between 11 to 33 meters, which corresponded to the SNRs most revealing of the progressive effect of the selected natural noise (-8.8 dB to -18.4 dB). Our results showed that in such conditions, identity of vowels is mostly preserved, with the striking peculiarity of the absence of confusion in vowels. The results also confirmed the functional role of consonants during lexical identification. The extensive analysis of recognition scores, confusion patterns and associated acoustic cues revealed that sonorant, sibilant and burst properties were the most important parameters influencing phoneme recognition. . Altogether these analyses allowed us to extract a resistance scale from consonant recognition scores. We also identified specific perceptual consonant confusion groups depending of the place in the words (onset vs. coda). Finally our data suggested that listeners may access some acoustic cues of the CV transition, opening interesting perspectives for future studies.

Dataset Information

Using speech recognition technology to investigate the association between timing-related speech features and depression severity.

Publications

Using speech recognition technology to investigate the association between timing-related speech features and depression severity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets