Highly Efficient and Effective Techniques for Thai Syllable Speech Recognition

Tangwongsan, Supachai; Po-Aramsri, P.; Phoophuangpairoj, Rong

doi:10.1007/978-3-540-30502-6_19

Cited by 9 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speech recognition technology has progressed and Mel-frequency cepstral coefficients (MFCCs) are acoustic features that have been widely used in speech recognition [8][9][10]. The Hidden Markov Model (HMM) is an efficient method employed in speech recognition [11,12] to model signal phenomena. Furthermore, HMM multiple speech classifiers have been studied to improve a voice-controlled robot [13].…”

Section: Applied Mechanics and Materialsmentioning

confidence: 99%

Nondestructive Determination of Maturity of the Monthong Durian by Mel-Frequency Cepstral Coefficients (MFCCs) and Neural Network

Khunarsa

Mahawan

Nakjai

et al. 2016

AMM

View full text Add to dashboard Cite

The challenging for buyers around the globe to identify good quality of Durian. For several kinds of Durian, it may be difficult for buyers to determine the Durian quality by appearance. The ability to select only good quality Durian without cutting or cleaving is useful because buyers will not waste money ordering undesirable Durian.This paper proposes a nondestructive technique to determine the stages of maturity of durian fruits. The presented methodology utilizes the concept of pattern matching. We used the local knocking equipment to knock the durian for knocked-sound. After that the knocked-sound was analyzed and generated to Mel-frequency cepstral coefficients (MFCCs) that is used to train data for the classifier. Feed-Forward Neural Network was used for the classifier and can effectively classification the stages of maturity of durian fruits with accuracy rate more than 82%.

show abstract

Section: Applied Mechanics and Materialsmentioning

confidence: 99%

Nondestructive Determination of Maturity of the Monthong Durian by Mel-Frequency Cepstral Coefficients (MFCCs) and Neural Network

Khunarsa

Mahawan

Nakjai

et al. 2016

AMM

View full text Add to dashboard Cite

show abstract

“…Hidden Markov models (HMMs) are an efficient technique used by researchers to create acoustic models. These acoustic models are found in many speech recognition systems [1][2] and the HMMs of syllable units are efficiently used in speech recognition systems [3]. Mel Frequency Cepstral Coefficients (MFCCs) are acoustic features that have been widely used to recognize speech signals [1][2][3][4][5].…”

Section: Applied Mechanics and Materialsmentioning

confidence: 99%

“…These acoustic models are found in many speech recognition systems [1][2] and the HMMs of syllable units are efficiently used in speech recognition systems [3]. Mel Frequency Cepstral Coefficients (MFCCs) are acoustic features that have been widely used to recognize speech signals [1][2][3][4][5]. Furthermore, MFCC-based acoustic features and pitch contours extracted from human voices are used to determine tones in languages such as Thai, Cantonese and Vietnamese [6][7][8].…”

Section: Applied Mechanics and Materialsmentioning

confidence: 99%

Computerized Unripe and Ripe Durian Striking Sound Recognition Using Syllable-Based HMMs

Phoophuangpairoj

2013

AMM

View full text Add to dashboard Cite

Buying expensive agricultural produce and fruit such as durians that are unripe can result in a bad experience for a consumer and a loss in profit for a retailer. Therefore, the study of durian striking sounds to create an automatic method of recognizing the ripeness of durians without cutting or damaging them is interesting because it could benefit shoppers and the fruit industry. To solve the problem, the following method of recognizing unripe and ripe striking signals is proposed. First, in the recognition process, the spectral features of the signals are extracted. Then, acoustic models of durian striking sounds are created using syllable-based Hidden Markov Models (HMM). Finally, sequences of syllable-based unripe and ripe durians and defined possible durian ripeness results are applied to recognize the ripeness. Average ripeness recognition rates of more than 90.0% were achieved when using any number of strikes from one to five. When the number of strikes was limited to four and five, higher recognition rates of 95.0% and 92.0% were achieved for the untrained and unknown test sets, respectively. An average total recognition time of less than 80 milliseconds was taken to recognize the unripe and ripe durian striking sounds. The experimental results indicate that the proposed method is a time-efficient, accurate and effective way of recognizing durian ripeness.

show abstract

“…The HMM is an efficient way to model speech. The recognition accuracy of 97.84% is attained for Thai speaker-dependent singlesyllable words when using the CDHMM with the MFCC [3]. The discrete HMM is also used in Thai speaker-independent speech recognition and the highest accuracy of 86.75% is obtained for recognizing single-syllable words [4].…”

Section: Introductionmentioning

confidence: 99%

Boosting Thai Syllable Speech Recognition Using Acoustic Models Combination

Tangwongsan

Phoophuangpairoj

2008

2008 International Conference on Computer and Electrical Engineering

View full text Add to dashboard Cite

In this paper, a highly effective system for Thai speech recognition is proposed. The speech recognizer for so-called speaker-independent is created by using Continuous Density Hidden Markov Model (CDHMM). In the acoustic level, the models trained for both speaker genders, and for each separate gender are investigated and tested in terms of accuracy. Experimental evaluation shows that with the acoustic models combination, the accuracy could be improved considerably in the acoustic level. The acoustic combination can support spoken utterances from both genders and still provide the high accuracy simultaneously. Interestingly, when using the acoustic models combination, the syllable accuracy of 89.84% is achieved with 4.53% improvement over using the conventional acoustic models trained for both genders.

show abstract

Highly Efficient and Effective Techniques for Thai Syllable Speech Recognition

Cited by 9 publications

References 5 publications

Nondestructive Determination of Maturity of the Monthong Durian by Mel-Frequency Cepstral Coefficients (MFCCs) and Neural Network

Nondestructive Determination of Maturity of the Monthong Durian by Mel-Frequency Cepstral Coefficients (MFCCs) and Neural Network

Computerized Unripe and Ripe Durian Striking Sound Recognition Using Syllable-Based HMMs

Boosting Thai Syllable Speech Recognition Using Acoustic Models Combination

Contact Info

Product

Resources

About