MFCC-based Houston Toad Call Detection using LSTM

Bashit, Abdullah Al; Valles, Damian

doi:10.1109/ismcr47492.2019.8955667

Cited by 6 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DCT applied to the transformed Mel frequency coefficients produced a set of MFCC campestral coefficients. The cepstral coefficients are usually referred to as stationary features, the extra information about the dynamic features of the signal is obtained by computing first derivative of cepstral coefficients and it is called delta coefficients, the second order derivative is called delta-delta coefficients [15]. Figure 5(a)-(d) clearly shows the differences in the values of MFCC coefficients for the healthy signal compared with, hyperkinetic pathology signal, hypokinetic pathology signal, and reflux pathology signal.…”

Section: Mel-spectrummentioning

confidence: 99%

Classification of three pathological voices based on specific features groups using support vector machine

Altayeb

Al-Ghraibah

2022

IJECE

View full text Add to dashboard Cite

<span>Determining and classifying pathological human sounds are still an interesting area of research in the field of speech processing. This paper explores different methods of voice features extraction, namely: Mel frequency cepstral coefficients (MFCCs), zero-crossing rate (ZCR) and discrete wavelet transform (DWT). A comparison is made between these methods in order to identify their ability in classifying any input sound as a normal or pathological voices using support vector machine (SVM). Firstly, the voice signal is processed and filtered, then vocal features are extracted using the proposed methods and finally six groups of features are used to classify the voice data as healthy, hyperkinetic dysphonia, hypokinetic dysphonia, or reflux laryngitis using separate classification processes. The classification results reach 100% accuracy using the MFCC and kurtosis feature group. While the other classification accuracies range between~60% to~97%. The Wavelet features provide very good classification results in comparison with other common voice features like MFCC and ZCR features. This paper aims to improve the diagnosis of voice disorders without the need for surgical interventions and endoscopic procedures which consumes time and burden the patients. Also, the comparison between the proposed feature extraction methods offers a good reference for further researches in the voice classification area.</span>

show abstract

Section: Mel-spectrummentioning

confidence: 99%