Myanmar Continuous Speech Recognition System Using Fuzzy Logic Classification in Speech Segmentation

Chit, Yin Win; Khaing, Soe Soe

doi:10.1145/3193063.3193071

Cited by 4 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the analysis and processing tasks of music signals, feature extraction of music signals is required to provide services for the subsequent research. Time domain analysis, such as short-time energy and zero-crossing rate [11], involves a large amount of data in computation; therefore, frequency domain analysis is more commonly used in signal analysis.…”

Section: Frequency Analysis-based Feature Extractionmentioning

confidence: 99%

Improving piano music signal recognition through enhanced frequency domain analysis

Gao

2024

J. meas. eng.

View full text Add to dashboard Cite

Feature extraction is a crucial component in the analysis of piano music signals. This article introduced three methods for feature extraction based on frequency domain analysis, namely short-time Fourier transform (STFT), linear predictive cepstral coefficient (LPCC), and Mel-frequency cepstral coefficient (MFCC). An improvement was then made to the MFCC. The inverse MFCC (IMFCC) was combined with mid-frequency MFCC (MidMFCC). The Fisher criterion was used to select the 12-order parameters with the maximum Fisher ratio, which were combined into the F-MFCC feature for recognizing 88 single piano notes through a support vector machine. The results indicated that when compared with the STFT and LPCC, the MFCC exhibited superior performance in recognizing piano music signals, with an accuracy rate of 78.03 % and an F1 value of 85.92 %. Nevertheless, the proposed F-MFCC achieved a remarkable accuracy rate of 90.91 %, representing a substantial improvement by 12.88 % over the MFCC alone. These findings provide evidence for the effectiveness of the designed F-MFCC feature for piano music signal recognition as well as its potential application in practical music signal analysis.

show abstract

Section: Frequency Analysis-based Feature Extractionmentioning

confidence: 99%

Improving piano music signal recognition through enhanced frequency domain analysis

Gao

2024

J. meas. eng.

View full text Add to dashboard Cite

show abstract

“…The results exhibit that the foreseen biometric system results in higher security as for 88 rate than the transcendent unimodal distinctive confirmation structures. Win Chit, et al (2018). This paper proposes the timespace options and repeat territory decisions supported feathery information for consistent talk division task by methods for a nonlinear talk examination.…”

Section: Akhmedova Et Al (2018) Differential Evolution Andmentioning

confidence: 99%

Fuzzy Utilization in Speech Recognition and its Different Application

Fernandes¹,

Mannepalli²,

Saravanan³

et al. 2019

IJEAT

View full text Add to dashboard Cite

Talk affirmation is one among the basic zones in cutting edge talk process. The examination of talk affirmation may be a bit of an examination for "artificial intelligence" machines that may "hear" and "appreciate" the verbally communicated data. The customary ways for talk affirmation like HMM and DTW, are outrageously inconvenient and time excellent. As such formal Fuzzy justification may be an endeavor in cutting edge talk process for the convincing portrayal of talk affirmation in a couple of utilization. The approach masterminded in the midst of this paper streamlines the utilization of fuzzy in talk affirmation and make the data dealing with time shorter. The case considered in the midst of this paper is that the least mind boggling, i.e., the example of speaker dependence, little vocabulary and disconnected words. There are various spectral and common choices isolated from human talk. The present ways for tendency acknowledgment from voice use basically MFCC and Energy feature. This paper briefs an overview concerning the present work on talk feeling ID strong for completing more examination by feathery approach.

show abstract

Clustering based emotional speech recognition using fuzzy and K-means for tamil language

John,

Kusumanchi,

Ramamoorthi

et al. 2024

AIP Conference Proceedings

View full text Add to dashboard Cite

Myanmar Continuous Speech Recognition System Using Fuzzy Logic Classification in Speech Segmentation

Cited by 4 publications

References 4 publications

Improving piano music signal recognition through enhanced frequency domain analysis

Improving piano music signal recognition through enhanced frequency domain analysis

Fuzzy Utilization in Speech Recognition and its Different Application

Clustering based emotional speech recognition using fuzzy and K-means for tamil language

Contact Info

Product

Resources

About