An SVM-Based Mandarin Pronunciation Quality Assessment System

Ge, Fengpei; Pan, Fuping; Liu, Changliang; Dong, Bin; Chan, Shui Duen; Zhu, Xinhua; Yan, Yonghong

doi:10.1007/978-3-642-01216-7_27

Cited by 8 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Phoneme level posteriori has been used as the basic goodness of pronunciation scoring for computer-assisted language learning systems [6] [7]. As the size of phoneme set is about several tens or several hundreds, the calculation is reduced much.…”

Section: Related Workmentioning

confidence: 99%

Combining Phoneme Loop Posteriori with Decoding Posteriori as Confidence Measure for Speech Recognition in E-service

Sun¹,

Zhao²,

Liu³

et al. 2010

2010 International Conference on E-Education, E-Business, E-Management and E-Learning

Self Cite

View full text Add to dashboard Cite

This paper presents our confidence measure system for speech recognition to integrate with e-Service to make HumanComputer Interaction more convenient. In order to make the system more robust for practical usage, the confidence measure is optimized to improve its performance as well as speed, compared with traditional state based confidence measure. First, the decoding likelihood of the best path is normalized with all the survival paths to form the onepass-based posteriori. After decoding, when recognition result is available as well as the phoneme level division point, the phoneme loop posteriori based confidence is calculated. Different models are compared for speed and performance. Then they are combined to form the final confidence for the judgement. Experiments are designed, and the proposed confidence measure get a relative improvement of 20%, 19.33% for equal error rate and 37.19%, 35.17% of false acceptance rate for out-of-vocabulary set on the development sets and the test sets, with no loss of false rejection rate for in-vocabulary set.

show abstract

Section: Related Workmentioning

confidence: 99%

Combining Phoneme Loop Posteriori with Decoding Posteriori as Confidence Measure for Speech Recognition in E-service

Sun¹,

Zhao²,

Liu³

et al. 2010

2010 International Conference on E-Education, E-Business, E-Management and E-Learning

Self Cite

View full text Add to dashboard Cite

show abstract

“…3, the baseline system calculates PLPP of all phones of the voice to be assessed and uses their average value as the reading quality assessment feature, which was appointed as an effective method in the paper of Ge [13]. However, there are improvement space for this method.…”

Section: Cluster Plppmentioning

confidence: 99%

“…There is a study done by Zechner et al, whose system was based on large vocabulary continuous speech recognition (LVCSR) system, and phonetic sounds to be assessed were sent to LVCSR engine, and according to analyzing the recognition results, error ratio of recognition, numbers of silence, the multi-dimensional assessment features of reading quality is extracted, and then the features Copyright c 2012 The Institute of Electronics, Information and Communication Engineers are mapped to reading quality score [9]- [12]. Our previous systems is also based on Automatic Speech Recognition (ASR) technique, but we use forced alignment instead of LVCSR [13], which is different from the Zechner's method. Both the forced alignment and LVCSR have their advantages.…”

Section: Introductionmentioning

confidence: 99%

A Forced Alignment Based Approach for English Passage Reading Assessment

Zhang¹,

Pan²,

Dong³

et al. 2012

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYThis paper presents our investigation into improving the performance of our previous automatic reading quality assessment system. The method of the baseline system is calculating the average value of the Phone Log-Posterior Probability (PLPP) of all phones in the voice to be assessed, and the average value is used as the reading quality assessment feature. In this paper, we presents three improvements. First, we cluster the triphones, and then calculate the average value of the normalized PLPP for each classification separately, and use this average values as the multidimensional assessment features instead of the original one-dimensional assessment feature. This method is simple but effective, which made the score difference of the machine scoring and manual scoring decrease by 30.2% relatively. Second, in order to assess the reading rhythm, we train Gaussian Mixture Models (GMM), which contain the information of each triphone's relative duration under standard pronunciation. Using the GMM, we can calculate the probability that the relative duration of each phone is conform to the standard pronunciation, and the average value of the probabilities is added to the assessment feature vector as a dimension of feature, which decreased the score difference between the machine scoring and manual scoring by 9.7% relatively. Third, we detect Filled Pauses (FP) by analyzing the formant curve, and then calculate the relative duration of FP, and add the relative duration of FP to the assessment feature vector as a dimension of feature. This method made the score difference between the machine scoring and manual scoring be further decreased by 10.2% relatively. Finally, when the feature vector extracted by the three methods are used together, the score difference between the machine scoring and manual scoring was decreased by 43.9% relatively compared to the baseline system.

show abstract

“…The phoneme-level posterior was proposed in [8], [9]. To calculate the phoneme-level posterior directly for a segment using the same state-based HMM model, a phoneme loop should be constructed first.…”

Section: Phoneme-level Posteriormentioning

confidence: 99%

Enhancing the Robustness of the Posterior-Based Confidence Measures Using Entropy Information for Speech Recognition

Sun

Zhou

Zhao

et al. 2010

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYIn this paper, the robustness of the posterior-based confidence measures is improved by utilizing entropy information, which is calculated for speech-unit-level posteriors using only the best recognition result, without requiring a larger computational load than conventional methods. Using different normalization methods, two posterior-based entropy confidence measures are proposed. Practical details are discussed for two typical levels of hidden Markov model (HMM)-based posterior confidence measures, and both levels are compared in terms of their performances. Experiments show that the entropy information results in significant improvements in the posterior-based confidence measures. The absolute improvements of the out-of-vocabulary (OOV) rejection rate are more than 20% for both the phoneme-level confidence measures and the state-level confidence measures for our embedded test sets, without a significant decline of the in-vocabulary accuracy.

show abstract

An SVM-Based Mandarin Pronunciation Quality Assessment System

Cited by 8 publications

References 8 publications

Combining Phoneme Loop Posteriori with Decoding Posteriori as Confidence Measure for Speech Recognition in E-service

Combining Phoneme Loop Posteriori with Decoding Posteriori as Confidence Measure for Speech Recognition in E-service

A Forced Alignment Based Approach for English Passage Reading Assessment

Enhancing the Robustness of the Posterior-Based Confidence Measures Using Entropy Information for Speech Recognition

Contact Info

Product

Resources

About