This pilot study evaluates the ability of machined learned algorithms to assist with the differential diagnosis of dementia subtypes based on brief (< 10 min) spontaneous speech samples. We analyzed 1 recordings of a brief spontaneous speech sample from 48 participants from 5 different groups: 4 types of dementia plus healthy controls. Recordings were analyzed using a speech recognition system optimized for speakerindependent spontaneous speech. Lexical and acoustic features were automatically extracted. The resulting feature profiles were used as input to a machine learning system that was trained to identify the diagnosis assigned to each research participant. Between groups lexical and acoustic differences features were detected in accordance with expectations from prior research literature suggesting that classifications were based on features consistent with human-observed symptomatology. Machine learning algorithms were able to identify participants' diagnostic group with accuracy comparable to existing diagnostic methods in use today. Results suggest this clinical speech analytic approach offers promise as an additional, objective and easily obtained source of diagnostic information for clinicians.

Background: The diagnosis of posttraumatic stress disorder (PTSD) is usually based on clinical interviews or self-report measures. Both approaches are subject to underand over-reporting of symptoms. An objective test is lacking. We have developed a classifier of PTSD based on objective speech-marker features that discriminate PTSD cases from controls.Methods: Speech samples were obtained from warzone-exposed veterans, 52 cases with PTSD and 77 controls, assessed with the Clinician-Administered PTSD Scale.Individuals with major depressive disorder (MDD) were excluded. Audio recordings of clinical interviews were used to obtain 40,526 speech features which were input to a random forest (RF) algorithm. Results:The selected RF used 18 speech features and the receiver operating characteristic curve had an area under the curve (AUC) of 0.954. At a probability of PTSD cut point of 0.423, Youden's index was 0.787, and overall correct classification rate was 89.1%. The probability of PTSD was higher for markers that indicated slower, more monotonous speech, less change in tonality, and less activation.Depression symptoms, alcohol use disorder, and TBI did not meet statistical tests to be considered confounders.Conclusions: This study demonstrates that a speech-based algorithm can objectively differentiate PTSD cases from controls. The RF classifier had a high AUC. Further validation in an independent sample and appraisal of the classifier to identify those with MDD only compared with those with PTSD comorbid with MDD is required. K E Y W O R D S biomarkers, diagnostics, feature extraction, military, posttraumatic stress disorder, speechbased assessment, veterans

This paper introduces the Voices Obscured In Complex Environmental Settings (VOICES) corpus, a freely available dataset under Creative Commons BY 4.0. This dataset will promote speech and signal processing research of speech recorded by far-field microphones in noisy room conditions. Publicly available speech corpora are mostly composed of isolated speech at close-range microphony. A typical approach to better represent realistic scenarios, is to convolve clean speech with noise and simulated room response for model training. Despite these efforts, model performance degrades when tested against uncurated speech in natural conditions. For this corpus, audio was recorded in furnished rooms with background noise played in conjunction with foreground speech selected from the Lib-riSpeech corpus. Multiple sessions were recorded in each room to accommodate for all foreground speech-background noise combinations. Audio was recorded using twelve microphones placed throughout the room, resulting in 120 hours of audio per microphone. This work is a multi-organizational effort led by SRI International and Lab41 with the intent to push forward state-of-the-art distant microphone approaches in signal processing and speech recognition.

No abstract

No abstract