An Analytical Study of Speech Pathology Detection Based on MFCC and Deep Neural Networks

Zakariah, Mohammed; B, Reshma; Alotaibi, Yousef Ajami; Guo, Yanhui; Tran-Trung, Kiet; Elahi, Mohammad Mamun

doi:10.1155/2022/7814952

Cited by 24 publications

(9 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2022, Zakariah et al [39] have tried AI, DNN, and different types of feature analysis. Initially, audio from the patients was collected using DNN and those data were sent to three features for analysis to separate the health and affected sounds.…”

Section: Literature Surveymentioning

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

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%

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

“…The transformation formula from Mel-scale to Hz is related (9). The centre frequencies of the series bandpass filters are designed according to this perceptually motivated scale, the known variation of the human ear's critical bandwidths [32].…”

Section: Mel-frequency Cepstral Coefficientsmentioning

confidence: 99%

Speech-based gender recognition using linear prediction and mel-frequency cepstral coefficients

Ali

Noorsal

Mokhtar

et al. 2022

IJEECS

View full text Add to dashboard Cite

Gender discrimination and awareness are essentially practiced in social, education, workplace, and economic sectors across the globe. A person manifests this attribute naturally in gait, body gesture, facial, including speech. For that reason, automatic gender recognition (AGR) has become an interesting sub-topic in speech recognition systems that can be found in many speech technology applications. However, retrieving salient gender-related information from a speech signal is a challenging problem since speech contains abundant information apart from gender. The paper intends to compare the performance of human vocal tract-based model i.e., linear prediction coefficients (LPC) and human auditory-based model i.e., Mel-frequency cepstral coefficients (MFCC) which are popularly used in other speech recognition tasks by experimentation of optimal feature parameters and classifier’s parameters. The audio data used in this study was obtained from 93 speakers uttering selected words with different vowels. The two feature vectors were tested using two classification algorithms namely, discriminant analysis (DA) and artificial neural network (ANN). Although the experimental results were promising using both feature parameters, the best overall accuracy rate of 97.07% was recorded using MFCC-ANN techniques with almost equal performance for male and female classes.

show abstract

“…Mel-Frequency Cepstral Coefficient (MFCC) [10][11] is a frequency domain analysis method for sound signals, which has the advantages of no restriction on the types of input audio signals, strong anti-interference and good Rubon.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Mine Hoist Based on MFCC-SVDD

Wang¹,

Li²

2023

HSET

View full text Add to dashboard Cite

In the field of coal mine production, mine hoist plays a very important role in the whole mine transportation engineering. Its safety and stability directly affect the production efficiency of coal mine and the life safety of staff. In view of this, a fault diagnosis method of mine hoist based on MFCC-SVDD is proposed. By collecting the audio signal of the elevator, MFCC algorithm was used to extract the sound signal of multiple channels and the MEL frequency cepstrum coefficient was used to extract the fault characteristic parameters. Based on the one-class classifier SVDD, the hypersphere of the elevator was constructed to test and recognize the sound signals in the training, and the classification and recognition of the fault types of the elevator were completed. The MFCC characteristic parameters of 600 training samples were randomly selected as input to train the model, and 200 test samples were identified. The accuracy of fault identification reached 85%-96%, which provided a guarantee for mine production safety.

show abstract

An Analytical Study of Speech Pathology Detection Based on MFCC and Deep Neural Networks

Cited by 24 publications

References 50 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

Speech-based gender recognition using linear prediction and mel-frequency cepstral coefficients

Fault Diagnosis of Mine Hoist Based on MFCC-SVDD

Contact Info

Product

Resources

About