• Phonetics and Speech Sciences
• /
• v.6 no.4
• /
• pp.101-108
• /
• 2014

This study investigates the effects of Japanese learners' Korean segmental production on pronunciation evaluation by Korean native raters. Read speech from 24 learners whose native language is Japanese are transcribed at the phonemic level, and confusion matrices are generated based on the phonemic transcriptions. The deviance from the canonical pronunciation found in the learners' speech is analyzed in terms of phoneme substitutions, vowel insertions, and consonant deletions. Each learner's pronunciation is rated impressionistically by 5 Korean native raters. The result shows that the deviance from the canonical pronunciation is strongly correlated with the pronunciation evaluation scores. Especially, the rates of phoneme substitutions and vowel insertions which are very strongly correlated with the pronunciation evaluation scores.

• Phonetics and Speech Sciences
• /
• v.5 no.4
• /
• pp.109-119
• /
• 2013

The purpose of this paper is to show the tendency of evaluators in the pronunciation evaluation of English utterances. The tendency was visualized using the evaluation model of English pronunciation proposed in [1]. One hundred fifty female university students and four evaluators participated in the study. Students read eight English sentences aloud as evaluators evaluated English pronunciation by their own criteria. The models based on their pronunciation evaluation proved to be efficient in showing their evaluation tendency in terms of the fundamental frequency, intensity, segmental durations, and segmental spectra as compared to those of the five native speakers of English chosen for building the models. However, human evaluators were not always consistent in their evaluation and sometimes gave conflicting scores to the same students.

• Phonetics and Speech Sciences
• /
• v.2 no.4
• /
• pp.101-107
• /
• 2010

This study investigates the difference in the evaluation of English pronunciation quality between native speakers of English and Korean learners of English. This study employs a novel method of independently evaluating the prosody and segmentals of English sentences. A set of stimuli were made by swapping the prosody and the segmentals of English sentences read by a native speaker of American English and a Korean learner of English. Evaluations of the difference level of stimuli pairs and the goodness of the pronunciation quality showed that both native speakers of English and Korean learners of English give priority to the segmentals but native speakers of English were more sensitive to the difference in prosody in the evaluation of English pronunciation.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.131-136
• /
• 2016

An appropriate evaluation on learner's pronunciation has been an important part of foreign language education. The learners should be evaluated and receive proper feedback for pronunciation improvement. Due to the cost and consistency problem of human evaluation, automatic pronunciation evaluation system has been studied. The most of the current automatic evaluation systems utilizes underlying Automatic Speech Recognition (ASR) technology. We suggest in this work to evaluate learner's pronunciation accuracy and fluency in word-level using the ASR and non-native teacher's speech model. Through the performance evaluation on our system, we confirm the overall evaluation result of pronunciation accuracy and fluency actually represents the learner's English skill level quite accurately.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.119-122
• /
• 2000

In this paper, we implement an elementary system to correct accent, pronunciation, and intonation in English spoken by non-native English speakers. In case of the accent evaluation, energy and pitch information are used to find stressed syllables, and then we extract the segment information of input patterns using a dynamic time warping method to discriminate and evaluate accent position. For the pronunciation evaluation. we utilize the segment information using the same algorithm as in accent evaluation and calculate the spectral distance measure for each phoneme between input and reference. For the intonation evaluation. we propose nine pattern of slope to estimate pitch contour, then we grade test sentences by accumulated error obtained by the distance measure and estimated slope. Our result shows that 98 percent of accent and 71 percent of pronunciation evaluation agree with perceptual measure. As the result of the intonation evaluation. system represent the similar order of grade for the four sentences having different intonation patterns compared with perceptual evaluation.

• Phonetics and Speech Sciences
• /
• v.10 no.4
• /
• pp.111-119
• /
• 2018

This paper proposes a method to improve speech recognition performance by extracting various pronunciations of the pseudo-morpheme unit from an eojeol unit corpus and generating a new recognition unit considering pronunciation variations. In the proposed method, we first align the pronunciation of the eojeol units and the pseudo-morpheme units, and then expand the pronunciation dictionary by extracting the new pronunciations of the pseudo-morpheme units at the pronunciation of the eojeol units. Then, we propose a new recognition unit that relies on pronunciation by tagging the obtained phoneme symbols according to the pseudo-morpheme units. The proposed units and their extended pronunciations are incorporated into the lexicon and language model of the speech recognizer. Experiments for performance evaluation are performed using the Korean speech recognizer with a trigram language model obtained by a 100 million pseudo-morpheme corpus and an acoustic model trained by a multi-genre broadcast speech data of 445 hours. The proposed method is shown to reduce the word error rate relatively by 13.8% in the news-genre evaluation data and by 4.5% in the total evaluation data.

• Journal of Korean language education
• /
• v.28 no.3
• /
• pp.105-126
• /
• 2017

Intelligibility has been widely regarded as an appropriate goal for second language pronunciation teaching. Yet there are few empirical studies that focus on the intelligibility of Korean learners' pronunciation. Therefore, this mixed-methods study examined the relationship among native-like pronunciation, intelligible pronunciation, phonological fluency and comprehensibility. Furthermore, this study investigated how native-like pronunciation and intelligible pronunciation are measured differently in terms of actual pronunciation skills. In addition, this study examined how these two pronunciation styles mutually influence each other. The results of this study show that achieving native-like pronunciation is a much more difficult goal than achieving intelligible pronunciation. It further shows that foreign accented pronunciation has little to do with comprehensibility while better intelligibility is needed for clearer comprehensibility. To achieve better intelligibility, this study recommends pronunciation teaching based on segments, suprasegmentals and fluency as the focus on suprasegmentals and fluency teaching are more important to achieve a native-like pronunciation. Besides the focus on phonology, there are other social factors which could influence the evaluation of native-like pronunciation, but are not part of this study. These findings are expected to contribute not only to a better understanding of pronunciation, but also to a more comprehensive reevaluation and informed direction of pronunciation teaching and research.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.49-55
• /
• 2018

This paper aims to describe a knowledge-based pronunciation generation system for French. It has been reported that a rule-based pronunciation generation system outperforms most of the data-driven ones for French; however, only a few related studies are available due to existing language barriers. We provide basic information about the French language from the point of view of the relationship between orthography and pronunciation, and then describe our knowledge-based pronunciation generation system, which consists of morphological analysis, Part-of-Speech (POS) tagging, grapheme-to-phoneme generation, and phone-to-phone generation. The evaluation results show that the word error rate of POS tagging, based on a sample of 1,000 sentences, is 10.70% and that of phoneme generation, using 130,883 entries, is 2.70%. This study is expected to contribute to the development and evaluation of speech synthesis or speech recognition systems for French.

• Speech Sciences
• /
• v.7 no.2
• /
• pp.245-253
• /
• 2000

In this paper, we implement an elementary system to correct accents and pronunciations in English words spoken by non-native English speakers. In case of the accent evaluation, energy and pitch information are used to find stressed syllables, and then we extract the segment information of input patterns using a dynamic time warping method to discriminate and evaluate accent position. For the pronunciation evaluation, we utilize the segment information using the same algorithm as in accent evaluation, and perform the spectral distance measure for each phoneme between input patterns and reference patterns. Based on these spectral distances, we decide whether to recommend the pronunciation correction or not. Our results show that 98 percent of accent and 71 percent of pronunciation evaluation agree with the perceptual measure.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.19-25
• /
• 2020

This study examined thirty-one Korean students' pronunciation of an English passage using a speech recognition application, Speechnotes, and two Canadian raters' evaluations of their speech according to the International English Language Testing System (IELTS) band criteria to assess the possibility of using the application as a teaching aid for pronunciation education. The results showed that the grand average percentage of correctly recognized words was 77.7%. From the moderate recognition rate, the pronunciation level of the participants was construed as intermediate and higher. The recognition rate varied depending on the composition of the content words and the function words in each given sentence. Frequency counts of unrecognized words by group level and word type revealed the typical pronunciation problems of the participants, including fricatives and nasals. The IELTS bands chosen by the two native raters for the rainbow passage had a moderately high correlation with each other. A moderate correlation was reported between the number of correctly recognized content words and the raters' bands, while an almost a negligible correlation was found between the function words and the raters' bands. From these results, the author concludes that the speech recognition application could constitute a partial aid for diagnosing each individual's or the group's pronunciation problems, but further studies are still needed to match human raters.