Acoustic feature-based non-scorable response detection for an automated speaking proficiency assessment

Author(s):  
Je Hun Jeon ◽  
Su-Youn Yoon
2018 ◽  
Vol 7 (2.16) ◽  
pp. 98 ◽  
Author(s):  
Mahesh K. Singh ◽  
A K. Singh ◽  
Narendra Singh

This paper emphasizes an algorithm that is based on acoustic analysis of electronics disguised voice. Proposed work is given a comparative analysis of all acoustic feature and its statistical coefficients. Acoustic features are computed by Mel-frequency cepstral coefficients (MFCC) method and compare with a normal voice and disguised voice by different semitones. All acoustic features passed through the feature based classifier and detected the identification rate of all type of electronically disguised voice. There are two types of support vector machine (SVM) and decision tree (DT) classifiers are used for speaker identification in terms of classification efficiency of electronically disguised voice by different semitones.  


2012 ◽  
Vol 459 ◽  
pp. 518-522
Author(s):  
Min Ma

A significant portion of the Chinese characters is phonogram, whose phonetic part can be used for overall sound inference. Phonetic degree is an inherent problem in the inference because low phonetic degree implies little phonetic dependence between the phonogram and its phonetic components. Solving the phonetic degree problem requires association each phonogram with the acoustic features. This paper introduces acoustic feature-based clustering, a classifying model that divides the common phonogram by defining new similarity of the sounds. This allows phonetic degree to be evaluated more reasonable. We demonstrate the clustering outperformed the traditional empirical estimation by having more accurate and real expressiveness. Acoustic feature-based clustering output 48.6% as phonetic degree, less than the empirical claim which is around 75%. As a clustering classifier, our model is competitive with a much clearer boundary on the phonogram dataset


Author(s):  
Bin Hao ◽  
Xiali Hei

Many healthcare providers integrate biometric recognition/verification schemes into patient identification or other information security systems. While overcoming the disadvantages of using passwords, PINs, and tokens which may be forgotten, or stolen, biometric systems are susceptible to spoofing attacks, or presentation attacks. Liveness detection is an effective mechanism used to defeat a presentation attack. This chapter focuses on voice liveness detection in automatic speaker verification (ASV) systems. The authors explain the spoofing attacks to ASV systems comprising impersonation, voice conversion, speech synthesis, and replay and then present four types of liveness detection (anti-spoofing) methods used to mitigate ASV spoofing attacks: challenge-response-based methods, acoustic feature-based methods, hardware-based methods, and multi-modal biometric-based methods. This chapter analyzes the advantages and disadvantages of each kind of liveness detection method and proposes the possible application of voiceprint-based liveness detection schemes in the insulin pump system.


2019 ◽  
Vol 12 (1) ◽  
pp. 1059-1076 ◽  
Author(s):  
Karwan Mustafa Saeed ◽  
◽  
Shaik Abdul Malik Mohamad Ismail ◽  
Lin Siew Eng ◽  
◽  
...  

2018 ◽  
Vol 4 (1) ◽  
pp. 73-102 ◽  
Author(s):  
Rui Ma ◽  
Lynn E. Henrichsen ◽  
Troy L. Cox ◽  
Mark W. Tanner

Abstract Although pronunciation is an integral part of speaking, the role pronunciation plays in determining speaking-proficiency levels is unclear (Higgs & Clifford, 1982; Kang, 2013). To contribute to our understanding of this area, the research reported here investigated the relationship between English as a Second Language (ESL) learners’ pronunciation ability and their speaking-proficiency ratings. At an intensive English program (IEP) in the United States, a speaking test was administered to 223 ESL students. Their speaking proficiency was rated using an oral proficiency assessment based on standardized guidelines. In addition, their pronunciation was rated in six categories (vowels, consonants, word stress, sentence stress, intonation, and rhythm) by 11 raters using a rubric specifically developed and validated for this study. Many-Facet Rasch Measurement (MFRM) was used to estimate the students’ pronunciation ability, which was then compared to their speaking ability. The study found that sentence stress, rhythm, and intonation accounted for 41% of the variance in the speaking-proficiency test scores with sentence stress being the most powerful factor.


Sign in / Sign up

Export Citation Format

Share Document