Disentangled Latent Speech Representation for Automatic Pathological Intelligibility Assessment

Weise, Tobias; Klumpp, Philipp; Maier, Andreas; Noeth, Elmar; Heismann, Björn J.; Schuster, Maria; Yang, Seung Hee

doi:10.48550/arxiv.2204.04016

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2022, Weise et al [36] have applied voice conversion technology and auto-encoding architecture. Initially, the speech information was decomposed into different components such as content, pitch/intonation, timing/rhythm, and timbre.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

FATFA-based DRN: Feedback Artificial Tree Firefly Algorithm-Enabled Deep Residual Network for Pathological Speech Enhancement

Katkam¹

2023

JNACS

View full text Add to dashboard Cite

The voice is a most important tool for the communication among the people in their day-to-day life. However, any slight change in the voice production system may affect the quality of the voice. For the past years, researchers worked to develop an effective automatic system for the clinicians to perform a preventive diagnosis for detecting the voice pathologies in an early stage. In this paper, the Feedback Artificial Tree Firefly Algorithm (FATFA)-based Deep Residual Network (DRN) is developed for the pathological speech enhancement. Here, the Hanning window is employed for extracting the frames from the speech signals. The multiband spectral subtraction technique is utilized for improving the extracted frames from the speech signals. Additionally, the DRN classifier is used for enhancing the pathological speech signals where the employed classifier is trained by the proposed optimization algorithm, called FATFA. Here, the developed FATFA-based DRN is the integration of Feedback Artificial Tree (FAT) and Firefly Algorithm (FA). However, the developed pathological speech enhancement method achieved efficient performance in terms of Perceptual Evaluation of Speech Quality (PESQ), and Root Mean Square Error (RMSE) with a higher PESQ of 3.907, and lesser RMSE of 30.64, respectively.

show abstract

Section: Literature Surveymentioning

confidence: 99%

“…PESQ is a measure, which is used for computing the quality of the speech signal. (36) where, B represents the value of the asymmetrical disturbance, and A signifies the value of the average disturbance.…”

Section: Pesqmentioning

confidence: 99%

FATFA-based DRN: Feedback Artificial Tree Firefly Algorithm-Enabled Deep Residual Network for Pathological Speech Enhancement

Katkam¹

2023

JNACS

View full text Add to dashboard Cite

show abstract

Disentangled Latent Speech Representation for Automatic Pathological Intelligibility Assessment

Cited by 1 publication

References 0 publications

FATFA-based DRN: Feedback Artificial Tree Firefly Algorithm-Enabled Deep Residual Network for Pathological Speech Enhancement

FATFA-based DRN: Feedback Artificial Tree Firefly Algorithm-Enabled Deep Residual Network for Pathological Speech Enhancement

Contact Info

Product

Resources

About