Wavelet based feature extraction for the vowel sound

Hidayat, Risanuri; Priyatmadi,; Ikawijaya, Welly

doi:10.1109/icitsi.2015.7437702

Cited by 10 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pengaplikasian metode ekstrasi pada pengolahan ucapan untuk beberapa suku kata dan fonem telah dilakukan. Seperti menggunakan metode wavelet Daubechies [1], [2]. Namun tidak banyak penelitian mengenai fonem terhadap ucapan Bahasa Indonesia.…”

Section: Pendahuluanunclassified

Speech Recognition for Cleft Lip and Palate Voice and Standard Voice for Consonant Words /B/

Anggoro

Herdjunanto²,

Hidayat³

2019

Senatik

Self Cite

View full text Add to dashboard Cite

Advances in technology make speech recognition improve. But does speech recognition recognize the sounds of cleft lip and palate? this research uses the voice of cleft lip and palate to normal voice. With the letter / b / which is the letter for lip articulation. Words used include Clothes, Ash and Moist. The extraction method uses Mel Frequency Cepstral Coefficients (MFCC), the classification uses K-Nearest Neighbor (KNN) with K-Fold Cross-Validation as a test. The results show the accuracy above 70%. 75% in the word "Baju". 75% in the word "Abu". 83% in the word "Lembab".

show abstract

Section: Pendahuluanunclassified

Speech Recognition for Cleft Lip and Palate Voice and Standard Voice for Consonant Words /B/

Anggoro

Herdjunanto²,

Hidayat³

2019

Senatik

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are several previous studies that combining WT and ED for analysing both onedimensional (1-D) and two-dimensional (2-D) signal [5]- [12]. In [5], a new approach that combines the WT, Phase Space Recontruction (PSR), and ED, was proposed to classify the normal and the epileptic seizure EEG signals.…”

Section: Introductionmentioning

confidence: 99%

Wavelet Based Feature Extraction for The Indonesian CV Syllables Sound

2018

Self Cite

View full text Add to dashboard Cite

This paper proposes the comb ined methods of Wavelet Transform (WT) and Euclidean Distance (ED) to estimate the expected value of the possib ly feature vector of Indonesian syllab les. This research aims to find the b est properties in effectiveness and efficiency on performing feature extraction of each syllab le sound to b e applied in the speech recognition systems. This proposed approach which is the state-of-the-art of the previous study consist of three main phase. In the first phase, the speech signal is segmented and normalized. In the second phase, the signal is transformed into frequency domain b y using the WT. In the third phase, to estimate the expected feature vector, the ED algorithm is used. Th e result shows the list of features of each syllab les can b e used for the next research, and some recommendations on the most effective and efficient WT to b e used in performing syllab le sound recognition.

show abstract

“…Based on previous research [1,3,11], it was found that Daubechies 2 (db2) was the one of the effective mother wavelet. The Daubechies wavelet of class D-2N can be written as:…”

Section: Waveletmentioning

confidence: 99%

“…Feature Set 1 is the combination of the DWT and statistical (WS). The wavelet type used is db2 at the 7th level of decomposition [11]. Feature Set 2 is the RE features.…”

Section: Introductionmentioning

confidence: 99%

Syllables sound signal classification using multi-layer perceptron in varying number of hidden-layer and hidden-neuron

2018

Self Cite

View full text Add to dashboard Cite

Abstract. The research on signal processing of syllables sound signal is still the challenging tasks, due to non-stationary, speaker-dependent, variable context, and dynamic nature factor of the signal. In the process of classification using multi-layer perceptron (MLP), the process of selecting a suitable parameter of hidden neuron and hidden layer is crucial for the optimal result of classification. This paper presents a speech signal classification method by using MLP with various numbers of hidden-layer and hidden-neuron for classifying the Indonesian Consonant-Vowel (CV) syllables signal. Five feature sets were generated by using Discrete Wavelet Transform (DWT), Renyi Entropy, Autoregressive Power Spectral Density (AR-PSD) and Statistical methods. Each syllable was segmented at a certain length to form a CV unit. The results show that the average recognition of WRPSDS with 1, 2, and 3 hidden layers were 74.17%, 69.17%, and 63.03%, respectively.

show abstract

Wavelet based feature extraction for the vowel sound

Cited by 10 publications

References 7 publications

Speech Recognition for Cleft Lip and Palate Voice and Standard Voice for Consonant Words /B/

Speech Recognition for Cleft Lip and Palate Voice and Standard Voice for Consonant Words /B/

Wavelet Based Feature Extraction for The Indonesian CV Syllables Sound

Syllables sound signal classification using multi-layer perceptron in varying number of hidden-layer and hidden-neuron

Contact Info

Product

Resources

About