• Phonetics and Speech Sciences
• /
• v.7 no.2
• /
• pp.149-156
• /
• 2015

We propose a new method for automatic fluency scoring of English speaking tests spoken by nonnative speakers in a free-talking style. The proposed method is different from the previous methods in that it does not require the transcribed texts for spoken utterances. At first, an input utterance is segmented into a phone sequence by using a phone recognizer trained by using native speech databases. For each utterance, a feature vector with 6 features is extracted by processing the segmentation results of the phone recognizer. Then, fluency score is computed by applying support vector regression (SVR) to the feature vector. The parameters of SVR are learned by using the rater scores for the utterances. In computer experiments with 3 tests taken by 48 Korean adults, we show that speech rate, phonation time ratio, and smoothed unfilled pause rate are best for fluency scoring. The correlation of between the rater score and the SVR score is shown to be 0.84, which is higher than the correlation of 0.78 among raters. Although the correlation is slightly lower than the correlation of 0.90 when the transcribed texts are given, it implies that the proposed method can be used as a preprocessing tool for fluency evaluation of speaking tests.

• Korean Journal of Child Studies
• /
• v.20 no.3
• /
• pp.199-216
• /
• 1999

The 121 five-year-old Korean subjects of this study were divided in 3 groups based on their experience in learning a foreign language (English). A battery of tests was administered to measure spoken and written language ability and the 3 metalinguistic domains of phonological, semantic, and syntactic awareness. Spoken language ability was positively correlated with semantic and syntactic awareness. The relative importance of each metalinguistic domain varied with level of written language development. Phonological awareness was the only predictor of decoding. Syntactic awareness and phonological awareness were significant variables in sentence comprehension. Metalinguistic ability was a better predictor of written language development than spoken language ability. Foreign language learning experience had an effect on syntactic awareness: low experience was superior to no experience, but high experience was not superior to low experience.

• Phonetics and Speech Sciences
• /
• v.11 no.4
• /
• pp.81-87
• /
• 2019

The purpose of the current study is to investigate the realization of speech rhythm in English as spoken by Korean learners of English. The study particularly aims to examine the rhythm metrics of English read speech by learners who speak Busan or the South Kyungsang dialect of Korean. Twenty-four learners whose L1 is Busan Korean and eight native speakers of English read a passage wherein five sentences were segmented and labeled as vocalic and intervocalic intervals. Various rhythm metrics such as %V, Varcos, and Pairwise Variability Indexes (PVIs) were calculated. The results show that Korean learners read English sentences with significantly more vocalic and consonantal intervals at a slower speech rate than native English speakers. The analyses of rhythm metrics revealed that when the speech rate was not normalized, Korean learners' English showed more variability in the length of consonantal and vocalic intervals. However, speech-rate-normalized rhythm metrics for vocalic intervals indicated that Korean learners transferred their L1 rhythmic structures (a syllable-timed language) into their L2 speech (a stress-timed language). Overall, the results suggest that Korean learners' English reflects the rhythmic characteristics of their L1. The effect of the learners' L1 dialect on the realization of L2 speech rhythm is also speculated.

• Phonetics and Speech Sciences
• /
• v.13 no.4
• /
• pp.1-7
• /
• 2021

This study aims to enhance English pronunciation education for Korean students by examining the impact of standard Korean and Gyeongsang regional dialect on the articulation of English vowels. Data were obtained through the Korean-Spoken English Corpus (K-SEC). Seven Korean words and ten English mono-syllabic words were uttered by adult, male speakers of standard Korean and Gyeongsang regional dialect, in particular, speakers with little to no experience living abroad were selected. Formant frequencies of the recorded corpus data were measured using spectrograms, provided by the speech analysis program, Praat. The recorded data were analyzed using the articulatory graph for formants. The results show that in comparison with speakers using standard Korean, those using the Gyeongsang regional dialect articulated both Korean and English vowels in the back. Moreover, the contrast between standard Korean and Gyeongsang regional dialect in the pronunciation of Korean vowels (/으/, /어/) affected how the corresponding English vowels (/ə/, /ʊ/) were articulated. Regardless of the use of regional dialect, a general feature of vowel pronunciation among Korean people is that they show more narrow articulatory movements, compared with that of native English speakers. Korean people generally experience difficulties with discriminating tense and lax vowels, whereas native English speakers have clear distinctions in vowel articulation.

• Phonetics and Speech Sciences
• /
• v.10 no.2
• /
• pp.33-37
• /
• 2018

Korean students with much exposure to the relatively slow and clear speech used in most English classes in Korea can be expected to have difficulty understanding the casual style that is common in the everyday speech of English speakers. This research attempted to investigate an effective way to utilize casual speech in English education, by exploring the way different speech styles (clear vs. casual) affect Korean learners' comprehension of spoken English. Twenty Korean university students and two native speakers of English participated in a listening session. The English utterances were produced in different speech styles (clear slow, casual slow, clear fast, and casual fast). The Korean students were divided into two groups by English proficiency level. The results showed that the Korean students achieved 69.4% comprehension accuracy, while the native speakers of English demonstrated almost perfect results. The Korean students (especially the low-proficiency group) had more problems perceiving function words than they did perceiving content words. Responding to the different speech styles, the high-proficiency group had more difficulty listening to utterances with phonological variation than they did listening to utterances produced at a faster speed. The low-proficiency group, however, struggled with utterances produced at a faster speed more than they did with utterances with phonological variation. The pedagogical implications of the results are discussed in the concluding section.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.127-136
• /
• 2024

The Korean language has written (formal) and spoken (phonetic) forms that differ in their application, which can lead to confusion, especially when dealing with numbers and embedded Western words and phrases. This fact makes it difficult to automate Korean speech recognition models due to the need for a complete transcription training dataset. Because such datasets are frequently constructed using broadcast audio and their accompanying transcriptions, they do not follow a discrete rule-based matching pattern. Furthermore, these mismatches are exacerbated over time due to changing tacit policies. To mitigate this problem, we introduce a data-driven Korean spoken-to-written transcription conversion technique that enhances the automatic conversion of numbers and Western phrases to improve automatic translation model performance.

• MALSORI
• /
• no.46
• /
• pp.87-102
• /
• 2003

In this paper, we present an English pronunciation correction system for Korean speakers and show some of experimental results on it. The aim of the system is to detect mispronounced phonemes in spoken words and to give appropriate correction comments to users. There are several English pronunciation correction systems adopting speech recognition technology, however, most of them use conventional speech recognition engines. From this reason, they could not give phoneme based correction comments to users. In our system, we build two kinds of phoneme models: standard native speaker models and Korean's error models. We also design recognition network based on phonemes to detect Koreans' common mispronunciations. We get 90% detection rate in insertion/deletion/replacement of phonemes, but we cannot get high detection rate in diphthong split and accents.

• The Journal of the Korea Contents Association
• /
• v.20 no.11
• /
• pp.378-390
• /
• 2020

English stress plays such a critical role in understanding spoken English words that its misplacement can lead to a breakdown of communication. Korean learners of English, whose native language is known to lack this feature, are expected to have some difficulty acquiring this English prosodic system. This study explored how Korean is different from English in manifesting prominence at the word level and how the interlanguage of Korean learners of English is dissimilar to both languages in that regard. Four polysyllabic English loanwords in Korean and their English source words were used as stimuli. Ten native English speakers read the English source words while ten Korean learners of English read the English loan words first and then the English source words. The analysis of 120 speech samples revealed that Korean words did not have any salient syllable realized by all stress features: duration, amplitude, and F0. On the contrary, English words had syllables with relative prominence, which was consistently manifested by all the features. Interestingly, in realizing English stress, the interlanguage of the Korean English learners bore more resemblance to that of English than that of their native language.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.3
• /
• pp.17-26
• /
• 1999

We present the first speech coarticulation database of Korean, English and Konglish/sup 3)/ named "SORIDA"/sup 4)/, which is designed to cover the maximum number of representations of coarticulation in these languages [1]. SORIDA features a compact database which is designed to contain a maximum number of triphones in a minimum number of prompts. SORIDA contains all consonantal triphones and vowel allophones in 682 Korean prompts of word length and in 717 English prompt words, spoken five times by speakers of balanced genders, dialects and ages. Korean prompts are synthesized lexicons which maximize their coarticulation variation disregarding any stress phenomena, while English prompts are natural words that fully reflect their stress effects with respect to the coarticulation variation. The prompts are designed differently because English phonology has stress while Korean does not. An intermediate language, Konglish has also been modeled by two Korean speakers reading 717 English prompt words. Recording was done in a controlled laboratory environment with an AKG Model C-100 microphone and a Fostex D-5 digital-audio-tape (DAT) recorder. The total recording time lasted four hours. SORIDA CD-ROM is available in one disk of 22.05 kHz sampling rate with a 16 bit sample size. SORIDA digital audio-tapes are available in four 124-minute-tapes of 48 kHz sampling rate. SORIDA′s list of phonetically-rich-words is also available in English and Korean.

• Phonetics and Speech Sciences
• /
• v.6 no.4
• /
• pp.17-26
• /
• 2014

The present study examined epenthetic vowels produced by Korean learners of English in read sentences, in terms of acoustic measures and extra-phonological factors. The results demonstrated three main findings. First, epenthetic vowels had relatively high F1 values and a wide range of F2 values. Most of the epenthetic vowels were inserted near Korean high central vowels, but some vowels were inserted near front vowels due to co-articulation with surrounding vowels. Second, vowel epenthesis was affected by the context. The results showed that the epenthesis was frequently seen with word junctions between obstruents (e.g., stops-fricatives). Third, Korean learners were not affected by English background and were very weakly affected by orthography. English experience, which is one of the extra-phonological factors, was not related to epenthesis production. However, orthography, the other extra-phonological factor, very weakly affected the amount of epenthesis production. Nine percent of all epenthesis production was affected by the English past-tense suffix '-ed'; approximately 70% of the participants were affected by this suffix. The findings of the present study contributed to understanding vowel epenthesis. First, the study revealed that the epenthetic vowels produced by Korean learners of English were close to the high central vowel, supporting previous studies that the epenthetic vowel is quite close to the shortest vowel. Second, the study examined the various phonetic environments of epenthetic vowels, revealing that vowel epenthesis occurred more frequently in a certain phonetic circumstance.