Neural network speaker dependent isolated Malay speech recognition system: handcrafted vs genetic algorithm

Salam, Md. Sah; Mohamad, Dzulkifli; Salleh, Sheikh Hussain Shaikh

doi:10.1109/isspa.2001.950252

Cited by 14 publications

(10 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a two-step search algorithm where the absolute energy (AE) for a coarse search is first used [19]. The speech signal was first divided into 50% overlapping frames of 10ms and then passed through a rectangular window [30,31]. The AE was computed by summing the absolute magnitudes of speech samples in each frame as shown in (3).…”

Section: Short-term Energy Algorithmmentioning

confidence: 99%

Hybrid methods of brandt’s generalised likelihood ratio and short-term energy for malay word speech segmentation

Seman

Norazam

2019

IJEECS

View full text Add to dashboard Cite

<p>Speech segmentation is an important part for speech recognition, synthesizing and coding. Statistical based approach detects segmentation points via computing spectral distortion of the signal without prior knowledge of the acoustic information proved to be able to give good match, less omission but lot of insertion. In this study the segmentation is done both manually and automatically using Malay words in traditional Malay poetry. This study proposed a hybrid method of Brandt’s generalized likelihood ratio (GLR) and short-term energy algorithm. The Brandt’s algorithm tries to estimate the abrupt change in energy to determine the segmentation points. A total of five Pantun are used in read mode and spoken by one male student in a noise free room. Experiments are conducted to see the the accuracy, insertion, and omission of the segmentation points. Experimental results show on average 80% accuracy with 0.2 second time tolerance for automatic segmentation with the algorithm having no knowledge of the acoustic characteristics<em>. </em></p>

show abstract

Section: Short-term Energy Algorithmmentioning

confidence: 99%

Hybrid methods of brandt’s generalised likelihood ratio and short-term energy for malay word speech segmentation

Seman

Norazam

2019

IJEECS

View full text Add to dashboard Cite

show abstract

“…Lim [9,10]. Another study includes Ting and Mark (2008) who converted Linear Predictive Coding (LPC) coefficients into cepstral coefficients before being fed into a Multi-layer Perceptron with one hidden layer for training and testing classifications [11].…”

Section: Researches In Malay Speech Recognitionmentioning

confidence: 99%

An Improved Feature Extraction Method for Malay Vowel Recognition based on Spectrum Delta

Azmi

2014

IJSEIA

View full text Add to dashboard Cite

show abstract

“…The start and endpoint locations were determined using only energy method. Noise level was calculated from the first 100ms or 800 samples, M using equation (6) which were assumed to be background noise.…”

Section: Pre-processing and Vowel Extractionmentioning

confidence: 99%

“…Among the active Malaysian Universities in researching Speech Recognition are Universiti Teknologi Malaysia (UTM), Universiti Kebangsaan Malaysia (UKM), Universiti Putra Malaysia (UPM), Universiti Sains Malaysia (USM) and Multimedia University (MMU). For example, UTM did research into Malay plosives sounds [3,4] and Malay numbers [5,6]. UTM also did a study on Malay vowels based on cepstral coefficients [7] and fusion of Dynamic Time Warping (DTW) and Hidden Markov Model (HMM) [8].…”

Section: Introductionmentioning

confidence: 99%

Vowel recognition using First Formant Feature

Azmi¹,

Yaacob²,

Paulraj³

2009

IJACT

View full text Add to dashboard Cite

Automatic speech recognition (ASR) has made great strides with the development of digital signal processing hardware and software especially using English as the language of choice. In this paper, a new feature extraction method is presented to identify vowels recorded from 80 Malaysian speakers. The features are obtained from Vocal Tract Model based on Bandwidth (BW) approach. Bandwidth approach identifies frequency ranges from the first formant peak of vowel spectrum. Mean magnitudes were calculated from these Bandwidth frequency ranges. Classification results from Bandwidth Approach were then compared with 13 MFCC Coefficients. A BPNN were used to classify the vowels. BW obtained a classification accuracy of 89.58%, which is 0.71% better than MFCC.

show abstract

Neural network speaker dependent isolated Malay speech recognition system: handcrafted vs genetic algorithm

Cited by 14 publications

References 1 publication

Hybrid methods of brandt’s generalised likelihood ratio and short-term energy for malay word speech segmentation

Hybrid methods of brandt’s generalised likelihood ratio and short-term energy for malay word speech segmentation

An Improved Feature Extraction Method for Malay Vowel Recognition based on Spectrum Delta

Vowel recognition using First Formant Feature

Contact Info

Product

Resources

About