Noise Robustness of Spectrum Delta (SpD) Features in Malay Vowel Recognition

Yusof, Shahrul Azmi Mohd; Idayu, Mahat Nor; Roshidi, D.; Yaakob, Abdul Razak; Yaacob, Sazali

doi:10.1007/978-3-642-35594-3_38

Search citation statements

Order By: Relevance

Paper Sections

Select...

Spectrum Delta Feature Extraction Methods1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2015

2021

Publication Types

Select...

Other1

Book1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The speech feature used in this study is Spectrum Delta developed by [11]. In this Spectral Delta approach, the differences in amplitude between each frequency band were used as features.…”

Section: Spectrum Delta Feature Extraction Methodsmentioning

confidence: 99%

Malay Word Pronunciation Application for Pre-school Children Using Vowel Recognition

Azmi¹

2015

2015 8th International Conference on U- And E-Service, Science and Technology (UNESST)

View full text Add to dashboard Cite

In Malaysia, many researchers focus on developing independent speaker speech recognition systems that use Malay Language or Bahasa Malaysia. Accuracy, noise robustness and processing time are concerns when developing speech therapy systems especially for children. In this study, a Malay word pronunciation test application is developed using Spectrum Delta (SPD) features and Logistic Regression classification model in an effort to improve Malay word pronunciation for pre-school children aged between 3-6 years old. Based on the 6 vowel classification rate, vowel /i/ were found to achieved the highest classification rate of 98.33% and vowel /o/ achieved the worst with 92.29%. Overall classification rate obtained was 95.11%. Results showed that the pronunciation application can assist children to improve their Malay word pronunciation. Vowel /i/, /e/, /o/ and /u/ are often mispronounced due to pronunciation habits.

show abstract

“…The speech feature used in this study is Spectrum Delta developed by [11]. In this Spectral Delta approach, the differences in amplitude between each frequency band were used as features.…”

Section: Spectrum Delta Feature Extraction Methodsmentioning

confidence: 99%