Automated Assessment of Glottal Dysfunction Through Unified Acoustic Voice Analysis

Speech glottal flow has been predominantly described in the time-domain in past decades, the Liljencrants–Fant (LF) model being the most widely used in speech analysis and synthesis, despite its computational complexity. The causal/anti-causal linear model (LFCALM) was later introduced as a digital filter implementation of LF, a mixed-phase spectral model including both anti-causal and causal filters to model the vocal-fold open and closed phases, respectively. To further simplify computation, a causal linear model (LFLM) describes the glottal flow with a fully causal set of filters. After expressing these three models under a single analytic formulation, we assessed here their perceptual consistency, when driven by a single parameter Rd related to voice quality. All possible paired combinations of signals generated using six Rd levels for each model were presented to subjects who were asked whether the two signals in each pair differed. Model pairs LFLM–LFCALM were judged similar when sharing the same Rd value, and LF was considered the same as LFLM and LFCALM given a consistent shift in Rd. Overall, the similarity between these models encourages the use of the simpler and more computationally efficient models LFCALM and LFLM in speech synthesis applications.

show abstract

Mouth Sounds: A Review of Acoustic Applications and Methodologies

Naal-Ruiz

Gonzalez-Rodriguez

Navas-Reascos

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Mouth sounds serve several purposes, from the clinical diagnosis of diseases to emotional recognition. The following review aims to synthesize and discuss the different methods to apply, extract, analyze, and classify the acoustic features of mouth sounds. The most analyzed features were the zero-crossing rate, power/energy-based, and amplitude-based features in the time domain; and tonal-based, spectral-based, and cepstral features in the frequency domain. Regarding acoustic feature analysis, t-tests, variations of analysis of variance, and Pearson’s correlation tests were the most-used statistical tests used for feature evaluation, while the support vector machine and gaussian mixture models were the most used machine learning methods for pattern recognition. Neural networks were employed according to data availability. The main applications of mouth sound research were physical and mental condition monitoring. Nonetheless, other applications, such as communication, were included in the review. Finally, the limitations of the studies are discussed, indicating the need for standard procedures for mouth sound acquisition and analysis.

show abstract

Automated Assessment of Glottal Dysfunction Through Unified Acoustic Voice Analysis

Cited by 3 publications

References 36 publications

Measurement of Formant Frequency in /hVd/ Words of Distorted Speech in Adult New Zealanders

Measurement of Formant Frequency in /hVd/ Words of Distorted Speech in Adult New Zealanders

Perceptual equivalence of the Liljencrants–Fant and linear-filter glottal flow models

Mouth Sounds: A Review of Acoustic Applications and Methodologies

Contact Info

Product

Resources

About