The aprosody of schizophrenia: Computationally derived acoustic phonetic underpinnings of monotone speech

Compton, Michael T.; Lunden, Anya; Cleary, Sean D.; Pauselli, Luca; Alolayan, Yazeed; Halpern, B; Broussard, Beth; Crisafio, Anthony; Capulong, Leslie; Balducci, Pierfrancesco Maria; Bernardini, Francesco; Covington, Michael A.

doi:10.1016/j.schres.2018.01.007

Cited by 51 publications

(54 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applications for understanding SMI are relatively limited, though links between reduced MFCC and clinically rated depression in adults (e.g., with 80% classification accuracy 46 ) and adolescents (e.g., with 61.1% classification accuracy 47 ) have been observed. Moreover, Compton et al 12,42 have demonstrated statistically significant relationships between formant frequencies and clinically rated negative symptoms (e.g., r = −0.45 12 ). In short, clinicians appear to be intuitively evaluating a much broader feature set than is included in most prior studies.…”

Section: Discussionmentioning

confidence: 98%

“…These features have not been typically examined in the context of SMI, as they are not captured by the VOXCOM or CANS systems (refs. 40,41 ; but see 12,42 for an exception). Collectively, these features concern the spectral quality and richness or speech, reflecting the involvement of a much broader vocal system than those typically involved in psychopathology research, e.g., "pitch" and "volume".…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Using machine learning of computerized vocal expression to measure blunted vocal affect and alogia

Cohen

Cox

et al. 2020

npj Schizophr

View full text Add to dashboard Cite

Negative symptoms are a transdiagnostic feature of serious mental illness (SMI) that can be potentially “digitally phenotyped” using objective vocal analysis. In prior studies, vocal measures show low convergence with clinical ratings, potentially because analysis has used small, constrained acoustic feature sets. We sought to evaluate (1) whether clinically rated blunted vocal affect (BvA)/alogia could be accurately modelled using machine learning (ML) with a large feature set from two separate tasks (i.e., a 20-s “picture” and a 60-s “free-recall” task), (2) whether “Predicted” BvA/alogia (computed from the ML model) are associated with demographics, diagnosis, psychiatric symptoms, and cognitive/social functioning, and (3) which key vocal features are central to BvA/Alogia ratings. Accuracy was high (>90%) and was improved when computed separately by speaking task. ML scores were associated with poor cognitive performance and social functioning and were higher in patients with schizophrenia versus depression or mania diagnoses. However, the features identified as most predictive of BvA/Alogia were generally not considered critical to their operational definitions. Implications for validating and implementing digital phenotyping to reduce SMI burden are discussed.

show abstract

Section: Discussionmentioning

confidence: 98%

Section: Discussionmentioning

confidence: 99%

Using machine learning of computerized vocal expression to measure blunted vocal affect and alogia

Cohen

Cox

et al. 2020

npj Schizophr

View full text Add to dashboard Cite

show abstract

“…A different approach involves the use of automated analysis of speech to identify acoustic features of vocal production, arguably with a greater reliability, sensitivity and validity. However, such studies have so far reported smaller and seemingly more contradictory findings: some indicate slower speech (Tavano et al, 2008), more pronounced pauses (Cannizzaro et al, 2005;Martínez-Sánchez et al, 2015;Rapcan et al, 2010) and reduced prosodic variability (Compton et al, 2018;Martínez-Sánchez et al, 2015;; while others indicate no reliable acoustic differences between 6 VOICE IN SCHIZOPHRENIA: REVIEW AND META-ANALYSIS individuals with schizophrenia and HC (Cohen et al, 2016;Docherty, 2012;Meaux et al, 2018). A meta-analysis of 13 studies suggests large differences between individuals with schizophrenia and HC on pause and speech duration, and more modest on intensity and pitch variability.…”

Section: Introductionmentioning

confidence: 99%

Voice Patterns in Schizophrenia: A systematic Review and Bayesian Meta-Analysis

Parola

Simonsen

Bliksted

et al. 2019

Preprint

View full text Add to dashboard Cite

Voice atypicalities have been a characteristic feature of schizophrenia since its first definitions. They are often associated with core negative symptoms such as flat affect and alogia, and with the social impairments seen in the disorder. This suggests that voice atypicalities may represent a marker of clinical features and social functioning in schizophrenia. We systematically reviewed and meta-analyzed the evidence for distinctive acoustic patterns in schizophrenia, as well as their relation to clinical features. We identified 46 articles, including 55 studies with a total of 1254 patients with schizophrenia and 699 healthy controls. Summary effect sizes (Hedges'g and Pearson's r) estimates were calculated using multilevel Bayesian modeling. We identified weak atypicalities in pitch variability (g = -0.55) related to flat affect, and stronger atypicalities in proportion of spoken time, speech rate, and pauses (g's between -0.75 and -1.89) related to alogia and flat affect. However, the effects were mostly modest (with the important exception of pause duration) compared to perceptual and clinical judgments, and characterized by large heterogeneity between studies.Moderator analyses revealed that tasks with a more demanding cognitive and social component showed larger effects both in contrasting patients and controls and in assessing symptomatology. In conclusion, studies of acoustic patterns are a promising but, yet unsystematic avenue for establishing markers of schizophrenia. We outline recommendations towards more cumulative, open, and theory-driven research.

show abstract

“…Vocal acoustic analysis is also capable of measuring the severity of negative symptoms such as aprosodia. Compton et al (2018) analyzed audio recordings of schizophrenic patients with aprosodia, schizophrenic patients without aprosodia, and healthy controls, and compared variability in pitch (F0), first (F1) and second (F2) formants, and intensity/loudness. Their results showed significant differences among groups, with the group with aprosodia showing reduced variability in pitch, F2, and intensity/loudness than other groups.…”

Section: Related Workmentioning

confidence: 99%

Vocal acoustic analysis and machine learning for the identification of schizophrenia

et al. 2020

View full text Add to dashboard Cite

Purpose Psychiatry still needs objective biomarkers. In the context of schizophrenia, there are speech abnormalities such as tangentiality, derailment, alogia, neologisms, poverty of speech, and aprosodia. There is a growing interest in speech signals features as possible indicators of schizophrenia. This article aims to develop an intelligent tool for detection of schizophrenia using vocal patterns and machine learning techniques. The main advantages of this type of solution are the low cost, high performance, and for being non-invasive. Methods Thirty-one individuals over 18 years old were selected, 20 with previous diagnosis of schizophrenia, and 11 healthy controls. Their speech was audio-recorded in naturalistic settings, during a routine medical assessment for psychiatric patients. In the case of healthy patients, the recordings were made in different environments. Recordings were pre-processed, excluding non-participant voices. We extracted 33 features. We used the particle swarm optimization algorithm for feature selection. Results The classifiers' performance was analyzed with four metrics: accuracy, sensibility, specificity, and kappa index. Best results were achieved when considering all 33 extracted features. Within machine models, support vector machines (SVM) models provided the greatest classification performance, with mean accuracy of 91.76% for PUK kernel. Our results outperform those from most studies published so far for the detection of schizophrenia based on acoustic patterns. Conclusion The use of machine learning classifiers using vocal parameters, in particular SVM, has shown to be very promising for the detection of schizophrenia. Nevertheless, further experiments with a larger sample will be necessary to validate our findings.

show abstract

The aprosody of schizophrenia: Computationally derived acoustic phonetic underpinnings of monotone speech

Abstract: Findings could represent a step toward developing new methods for measuring and tracking the severity of this specific negative symptom using acoustic phonetic parameters; such work is relevant to other psychiatric and neurological disorders.

Cited by 51 publications

References 34 publications

Using machine learning of computerized vocal expression to measure blunted vocal affect and alogia

Using machine learning of computerized vocal expression to measure blunted vocal affect and alogia

Voice Patterns in Schizophrenia: A systematic Review and Bayesian Meta-Analysis

Vocal acoustic analysis and machine learning for the identification of schizophrenia

Contact Info

Product

Resources

About