Multi-Dimensional Variation in Adult Speech as a Function of Age

A machine learning method to process voice samples for identification of Parkinson's disease

Machine learning approaches have been used for the automatic detection of Parkinson's disease with voice recordings being the most used data type due to the simple and non-invasive nature of acquiring such data. Although voice recordings captured via telephone or mobile devices allow much easier and wider access for data collection, current conflicting performance results limit their clinical applicability. This study has two novel contributions. First, we show the reliability of personal telephone-collected voice recordings of the sustained vowel /a/ in natural settings by collecting samples from 50 people with specialist-diagnosed Parkinson's disease and 50 healthy controls and applying machine learning classification with voice features related to phonation. Second, we utilize a novel application of a pre-trained convolutional neural network (Inception V3) with transfer learning to analyze the spectrograms of the sustained vowel from these samples. This approach considers speech intensity estimates across time and frequency scales rather than collapsing measurements across time. We show the superiority of our deep learning model for the task of classifying people with Parkinson's disease as distinct from healthy controls.

Comparison of In-Person and Online Recordings in the Clinical Teleassessment of Speech Production: A Pilot Study

In certain circumstances, speech and language therapy is proposed in telepractice as a practical alternative to in-person services. However, little is known about the minimum quality requirements of recordings in the teleassessment of motor speech disorders (MSD) utilizing validated tools. The aim here is to examine the comparability of offline analyses based on speech samples acquired from three sources: (1) in-person recordings with high quality material, serving as the baseline/gold standard; (2) in-person recordings with standard equipment; (3) online recordings from videoconferencing. Speech samples were recorded simultaneously from these three sources in fifteen neurotypical speakers performing a screening battery of MSD and analyzed by three speech and language therapists. Intersource and interrater agreements were estimated with intraclass correlation coefficients on seventeen perceptual and acoustic parameters. While the interrater agreement was excellent for most speech parameters, especially on high quality in-person recordings, it decreased in online recordings. The intersource agreement was excellent for speech rate and mean fundamental frequency measures when comparing high quality in-person recordings to the other conditions. The intersource agreement was poor for voice parameters, but also for perceptual measures of intelligibility and articulation. Clinicians who plan to teleassess MSD should adapt their recording setting to the parameters they want to reliably interpret.

A Longitudinal Study of Speech Acoustics in Older French Females: Analysis of the Filler Particle euh across Utterance Positions

Aging in speech production is a multidimensional process. Biological, cognitive, social, and communicative factors can change over time, stay relatively stable, or may even compensate for each other. In this longitudinal work, we focus on stability and change at the laryngeal and supralaryngeal levels in the discourse particle euh produced by 10 older French-speaking females at two times, 10 years apart. Recognizing the multiple discourse roles of euh, we divided out occurrences according to utterance position. We quantified the frequency of euh, and evaluated acoustic changes in formants, fundamental frequency, and voice quality across time and utterance position. Results showed that euh frequency was stable with age. The only acoustic measure that revealed an age effect was harmonics-to-noise ratio, showing less noise at older ages. Other measures mostly varied with utterance position, sometimes in interaction with age. Some voice quality changes could reflect laryngeal adjustments that provide for airflow conservation utterance-finally. The data suggest that aging effects may be evident in some prosodic positions (e.g., utterance-final position), but not others (utterance-initial position). Thus, it is essential to consider the interactions among these factors in future work and not assume that vocal aging is evident throughout the signal.