Biology subjects

Fusaroli, R.

Publications and source records attributed to Fusaroli, R..

5 recordsLinked to original sources

bioRxiv2021

Vocal markers of Autism Spectrum Disorder: assessing the generalizability of machine learning models

Machine learning (ML) approaches show increasing promise in their ability to identify vocal markers of autism. Nonetheless, it is unclear to what extent such markers generalize to new speech samples collected e.g., using a different speech task or in a different language. In this paper, we systematically assess the generalizability of ML findings across a variety of contexts. We train promising published ML models of vocal markers of autism on novel cross-linguistic datasets following a rigorous pipeline to minimize overfitting, including cross-validated training and ensemble models. We test the generalizability of the models by testing them on i) different participants from the same study, performing the same task; ii) the same participants, performing a different (but similar) task; iii) a different study with participants speaking a different language, performing the same type of task. While model performance is similar to previously published findings when trained and tested on data from the same study (out-of-sample performance), there is considerable variance between studies. Crucially, the models do not generalize well to different, though similar, tasks and not at all to new languages. The ML pipeline is openly shared. Generalizability of ML models of vocal markers of autism is an issue. We outline three recommendations for strategies researchers could take to be more explicit about generalizability and improve it in future studies. LAY SUMMARYMachine learning approaches promise to be able to identify autism from voice only. These models underestimate how diverse the contexts in which we speak are, how diverse the languages used are and how diverse autistic voices are. Machine learning approaches need to be more careful in defining their limits and generalizability.

bioinformatics↗

bioRxiv2021

A Generalizable Speech Emotion Recognition Model Reveals Depression and Remission

ObjectiveAffective disorders are associated with atypical voice patterns; however, automated voice analyses suffer from small sample sizes and untested generalizability on external data. We investigated a generalizable approach to aid clinical evaluation of depression and remission from voice using transfer learning: we train machine learning models on easily accessible non-clinical datasets and test them on novel clinical data in a different language. MethodsA Mixture-of-Experts machine learning model was trained to infer happy/sad emotional state using three publicly available emotional speech corpora in German and US English. We examined the models predictive ability to classify the presence of depression on Danish speaking healthy controls (N = 42), patients with first-episode major depressive disorder (MDD) (N = 40), and the subset of the same patients who entered remission (N = 25) based on recorded clinical interviews. The model was evaluated on raw, de-noised, and speaker-diarized data. ResultsThe model showed separation between healthy controls and depressed patients at the first visit, obtaining an AUC of 0.71. Further, speech from patients in remission was indistinguishable from that of the control group. Model predictions were stable throughout the interview, suggesting that 20-30 seconds of speech might be enough to accurately screen a patient. Background noise (but not speaker diarization) heavily impacted predictions. ConclusionA generalizable speech emotion recognition model can effectively reveal changes in speaker depressive states before and after remission in patients with MDD. Data collection settings and data cleaning are crucial when considering automated voice analysis for clinical purposes. Significant outcomes- Using a speech emotion recognition model trained on other languages, we predicted the presence of MDD with an AUC of 0.71. - The speech emotion recognition model could accurately detect changes in voice after patients achieved remission from MDD. - Preprocessing steps, particularly background noise removal, greatly influenced classification performance. Limitations- No data from non-remitters, meaning that changes to voice for that group could not be assessed. - It is unclear how well the model would generalize beyond Germanic languages. Data availability statementDue to the nature of the data (autobiographical interviews in a clinical population), the recordings of the participants cannot be shared publicly. The aggregated model predictions and code used to run the analyses is available at https://github.com/HLasse/SERDepressionDetection.

bioinformatics↗

bioRxiv2021

Towards a cumulative science of prosody in autism: a cross-linguistic meta-analysis-based investigation of acoustic markers in American and Danish autistic children

Acoustic atypicalities in speech production are argued to be potential markers of clinical features in Autism Spectrum Disorder (ASD). A recent meta-analysis highlighted shortcomings in the field, in particular small sample sizes and study heterogeneity (Fusaroli et al., 2017). We showcase a cumulative (i.e., explicitly building on previous studies both conceptually and statistically) yet self-correcting (i.e., critically assessing the impact of cumulative statistical techniques) approach to prosody in ASD to overcome these issues. We relied on the recommendations contained in the meta-analysis to build and analyze a cross-linguistic corpus of multiple speech productions in 77 autistic and 72 neurotypical children and adolescents (>1000 recordings in Danish and US English). We used meta-analytically informed and skeptical priors, with informed priors leading to more generalizable inference. We replicated findings of a minimal cross-linguistically reliable distinctive acoustic profile for ASD (higher pitch and longer pauses) with moderate effect sizes. We identified novel reliable differences between the two groups for normalized amplitude quotient, maxima dispersion quotient, and creakiness. However, the differences were small, and there is likely no one acoustic profile characterizing all autistic individuals. We identified reliable relations of acoustic features with individual differences (age, gender), and clinical features (speech rate and ADOS sub-scores). Besides cumulatively building our understanding of acoustic atypicalities in ASD, the study shows how to use systematic reviews and meta-analyses to guide the design and analysis of follow-up studies. We indicate future directions: larger and more diverse cross-linguistic datasets, focus on heterogeneity, self-critical cumulative approaches and open science. Lay SummaryAutistic individuals are reported to speak in distinctive ways. Distinctive vocal production can affect social interactions and social development and could represent a noninvasive way to support the assessment of ASD. We systematically checked whether acoustic atypicalities highlighted in previous articles could be actually found across multiple recordings and two languages. We find a minimal acoustic profile of ASD: higher pitch, longer pauses, increased hoarseness and creakiness of the voice. However, there is much individual variability (by age, sex, language, and clinical characteristics). This suggests that the search for one common "autistic voice" might be naive and more fine-grained approaches are needed.

bioinformatics↗

bioRxiv2019

Acoustic Measures of Prosody in Right-Hemisphere Damage: A Systematic Review and Meta-Analysis

The right hemisphere has often been claimed to be a locus for affective prosody, and people with right-hemisphere damage (RHD) have often been reported to show impairments in this domain. This phenomenon has been primarily investigated in terms of perception, more rarely in terms of production, and more rarely still using acoustic analysis. Our goal was to systematically review the papers reporting acoustic features of prosodic production in RHD, to identify strengths and weaknesses in this field, suggest guidelines for future research, and to support cumulative research by estimating the meta-analytic effect size of those features. We queried PubMed, PsychINFO, Web of Science, and Google Scholar, using the following combination of search terms: (prosody OR intonation OR inflection OR intensity OR pitch OR fundamental frequency OR speech rate OR voice quality) AND (RHD OR right hemisphere) AND (stroke) AND (acoustic). Standardized mean differences were extracted from all papers meeting inclusion criteria, and aggregated effect sizes were estimated using hierarchical Bayesian regression models. Sixteen papers met our inclusion criteria. We did not find strong evidence in the literature to indicate that the prosodic productions of people with RHD is substantially different from that of NBD controls, when measured in terms of acoustic features. However, the acoustic features of productions by people with RHD did differ from those of participants with NBD and LHD in some ways, notably in F0 variation and pause duration. Prosody type (emotional vs. linguistic) had very little effect. Taken together, currently available data show only a weak effect of RHD on prosody production. However, more accurate analyses are hindered by small sample sizes, lack of detail on lesion location, and divergent measuring techniques. Cumulative open science practices are recommended to overcome these issues.

bioinformatics↗

bioRxiv2019

Voice patterns in schizophrenia: A systematic review and Bayesian meta-analysis

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 (Hedgesg and Pearsons 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 (gs 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.

bioinformatics↗