• MALSORI
• /
• v.55
• /
• pp.103-118
• /
• 2005

In this paper, we describe a morpheme-based pronunciation lexicon useful for Korean LVCSR. The phonemic-context-dependent multiple pronunciation lexicon improves the recognition accuracy when cross-morpheme pronunciation variations are distinguished from within-morpheme pronunciation variations. Since adding all possible pronunciation variants to the lexicon increases the lexicon size and confusability between lexical entries, we have developed a lexicon pruning scheme for optimal selection of pronunciation variants to improve the performance of Korean LVCSR. By building a proposed pronunciation lexicon, an absolute reduction of $0.56\%$ in WER from the baseline performance of $27.39\%$ WER is achieved by cross-morpheme pronunciation variations model with a phonemic-context-dependent multiple pronunciation lexicon. On the best performance, an additional reduction of the lexicon size by $5.36\%$ is achieved from the same lexical entries.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.168-171
• /
• 2003

This study is about modeling pronunciation dictionary necessary for PLU(phoneme like unit) level word recognition. The recognition of nonnative speakers' pronunciation enables an automatic diagnosis and an error detection which are the core of English pronunciation tutoring system. The above system needs two pronunciation dictionaries. One is for representing standard English pronunciation. The other is for representing Korean speakers' English Pronunciation. Both dictionaries are integrated to generate pronunciation networks for variants.

• MALSORI
• /
• no.65
• /
• pp.93-103
• /
• 2008

In this paper, we propose a method for optimizing a multiple pronunciation dictionary used for modeling pronunciation variations of non-native speech. The proposed method removes some confusable pronunciation variants in the dictionary, resulting in a reduced dictionary size and less decoding time for automatic speech recognition (ASR). To this end, a confusability measure is first defined based on the Levenshtein distance between two different pronunciation variants. Then, the number of phonemes for each pronunciation variant is incorporated into the confusability measure to compensate for ASR errors due to words of a shorter length. We investigate the effect of the proposed method on ASR performance, where Korean is selected as the target language and Korean utterances spoken by Chinese native speakers are considered as non-native speech. It is shown from the experiments that an ASR system using the multiple pronunciation dictionary optimized by the proposed method can provide a relative average word error rate reduction of 6.25%, with 11.67% less ASR decoding time, as compared with that using a multiple pronunciation dictionary without the optimization.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.190-193
• /
• 2017

'서치 방지 단어'는 SNS 상에서 사용자들이 작성한 문서의 검색 및 수집을 피하기 위하여 사용하는 변이형을 뜻한다. 하나의 검색 키워드가 있다면 그와 같은 대상을 나타내는 변이형이 여러 형태로 존재할 수 있으며, 이들 변이형에 대한 검색 결과를 함께 수집할 수 있다면 데이터 확보가 중요하게 작용하는 다양한 연구에 큰 도움이 될 것이다. 본 연구에서는 특정 단어가 주어진 키워드로부터 의미 벡터 상의 거리가 가까울수록, 그리고 주어진 키워드와 비슷한 음성적 형태 즉 발음을 가질수록, 해당 키워드의 변이형일 가능성이 높을 것이라고 가정하였다. 이에 따라 단어 임베딩을 이용한 의미 유사도와 최소 편집 거리를 응용한 음성적 유사도를 이용하여 주어진 검색 키워드와 유사한 변이형들을 제안하고자 하였다. 그 결과 구성된 변이형 후보의 목록에는 다양한 형태의 단어들이 포함되었으며, 이들 중 다수가 실제 SNS 상에서 같은 의미로 사용되고 있음이 확인되었다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.190-193
• /
• 2017

'서치 방지 단어'는 SNS 상에서 사용자들이 작성한 문서의 검색 및 수집을 피하기 위하여 사용하는 변이형을 뜻한다. 하나의 검색 키워드가 있다면 그와 같은 대상을 나타내는 변이형이 여러 형태로 존재할 수 있으며, 이들 변이형에 대한 검색 결과를 함께 수집할 수 있다면 데이터 확보가 중요하게 작용하는 다양한 연구에 큰 도움이 될 것이다. 본 연구에서는 특정 단어가 주어진 키워드로부터 의미 벡터 상의 거리가 가까울수록, 그리고 주어진 키워드와 비슷한 음성적 형태 즉 발음을 가질수록, 해당 키워드의 변이형일 가능성이 높을 것이라고 가정하였다. 이에 따라 단어 임베딩을 이용한 의미 유사도와 최소 편집 거리를 응용한 음성적 유사도를 이용하여 주어진 검색 키워드와 유사한 변이형들을 제안하고자 하였다. 그 결과 구성된 변이형 후보의 목록에는 다양한 형태의 단어들이 포함되었으며, 이들 중 다수가 실제 SNS 상에서 같은 의미로 사용되고 있음이 확인되었다.

• Speech Sciences
• /
• v.13 no.3
• /
• pp.35-48
• /
• 2006

The present study examined whether words with higher frequency have more exposure to the lenition process such as intervocalic stop voicing or /h/ reduction in the production of the Korean speakers. Experiment 1 and Experiment 2 tested if word-internal intervocalic voicing and /h/ reduction occur more often in the words with higher frequency than less frequent words respectively. Results showed that the rate of voicing was not significantly different between the high frequency group and the low frequency group; rather both high and low frequency words were shown to be fully voiced in this prosodic position. However, intervocalic /h/s were deleted more in high frequency words than in low frequency words. Low frequency words showed that other phonetic variants such as [h] and [w] were found more often than in high frequency group. Thus the results of the present study are indefinitive as to the relationship between the word frequency and lenition with the data at hand.

• Proceedings of the KSPS conference
• /
• 1996.10a
• /
• pp.333-336
• /
• 1996

It is widely known that the Japanese alveolar nasal (n) is affected by adjacent vowels in most positions, that is, the variants of the alveolar (n) occur conditionally. The Japanese (n) is palatalized under the influence of vowel (i) or palatal (j). In the articulation of (ni), for instance, the tip and sides of the tongue make wide contact with the palate. It is interesting to know how palatalization occurs and varies during the production in different contexts. In my presentation, the actual realization of the palatalized alveolar nasal in different contexts is examined and clarified by consider me the Electro-palatographic data and examining the articulatory feel ins and auditory impression. As a result, palatalized (equation omitted) occurs either word-initially or inter-vocalically. (equation omitted) in (equation omitted) and (equation omitted) has great palatality. When conditioned by (j), the (equation omitted) in (equation omitted), (equation omitted) and (equation omitted) has full palatality. In each sound the average number of contacted electrodes of the Electro-palatograph at maximum tongue-palate contact is 63 or 100% of the total. To summarize the experimental data, articulatory feel ins and auditory impression, it can be concluded that the (n) followed by or hemmed in (i), (j) is a palatalized nasal (equation omitted).

• MALSORI
• /
• no.31_32
• /
• pp.223-238
• /
• 1996

It is widely hewn that the Japanese alveolar nasal [n] is affected by adjacent vowels in most positions, that is, the variants of the alveolar [n] occur conditionally. The Japanese [n] is palatalized under the influence of vowel [i] or palatal [j]. In the articulation of 'に', for instance, the tip and sides of the tongue make wide contact with the palate. It is interesting to know how palatalization occurs and varies during the production in different contexts. In my presentation the actual realization of the palatalized alveolar nasal in different contexts is examined and clarified by considering the Electro-palatographic data and examining the articulatory feeling and auditory impression. As a result, palatalized [${\eta}$] occurs either word-initially- or inter-vocalically. [${\eta}$] in [${\eta}$i] and 'いに'[$i{\eta}$] has great palatality. When conditioned by [j], the [${\eta}$] in 'にゃ'[${\eta}$ja], 'にょ'[${\eta}jo$] and 'にゅ'[${\eta}jw$] has full palatality. In each sound the average number of contacted electrodes of the Electro-palatograph at maximum tongue-palate contact is 63 or 100% of the total. To summarize the experimental data, articulatory feeling and auditory impression, it can be concluded that 'the [n] followed by or hemmed in [i], [j] is a palatalized nasal [${\eta}$].

• Language Facts and Perspectives
• /
• v.44
• /
• pp.357-397
• /
• 2018

The purpose of this paper is to investigate the phonemic errors in Korean learner's spoken corpus. Through this, we tried to investigate the common errors and the errors in certain languages. The results of the analysis were as follows. First, Errors that distinguish three phonemes(plain sound, tense sound, aspiration sound) were high in all languages. In the middle phonemes, the most common errors in pronouncing 'ㅓ' in all languages. Second, the errors of each language are different. Comparing the ratios by position, Chinese characters had the most common errors with 50% in final phoneme, and the Japanese language showed equal errors in initial, middle, and end. In English, initial phoneme errors accounted for 58%. Vietnamese Learners showed intensive errors in the initial and final phoneme. Third, in addition to the phoneme errors, we also examined the allophone errors and foreign language pronunciation errors. The allophone errors are mainly concentrated in 'ㄹ', ​​and the pronunciation of the foreign language is mainly used in the source language or the native language of the learners. This paper analyzes the phoneme errors in the Learner's spoken language through the spoken corpus data with representative and annotation consistency. Through this study, we could compare the difference of phoneme errors of Main Korean learners.

• Phonetics and Speech Sciences
• /
• v.2 no.4
• /
• pp.83-92
• /
• 2010

The present study examined how listeners of Seoul Korean would recover deleted phonemes in consonant cluster simplification. In a phoneme monitoring experiment, listeners had to monitor for C2 (/k/ or /p/) in C1C2C3 when C2 was deleted (C1 was preserved) or preserved (C1 was deleted). The target consonant (C2) was either /k/ or /p/ (e.g., i$\b{lk}$-t${\partial}$lato vs. pa$\b{lp}$-t${\partial}$lato), and there were two listener groups, one group tested in 2002 and the other in 2009. Some points have emerged from the results. First, listeners were able to detect deleted phonemes as accurately and rapidly as preserved phonemes, showing that the physical presence of the acoustic information did not improve the listeners' performance. This suggests that listeners must have relied on language-specific phonological knowledge about the consonant cluster simplification, rather than relying on the low-level acoustic-phonetic information. Second, listener groups (participants in 2002 vs. 2009), differed in processing /p/ versus /k/: listeners in 2009 failed to detect /p/ more frequently than those in 2002, suggesting that the way the consonant cluster sequence is produced and perceived has changed over time. This result was interpreted as coming from statistical patterns of speech production in contemporary Seoul Korean as reported in a recent study by Cho & Kim (2009): /p/ is deleted far more often than /p/ is preserved, which is likely reflected in the way listeners process simplified variants. Finally, listeners processed /k/ more efficiently than /p/, especially when the target was physically present (in C-preserved condition), indicating that listeners benefited more from the presence of /k/ than of /p/. This was interpreted as supporting the view that velars are perceptually more robust than labials, which constrains shaping phonological patterns of the language. These results were then discussed in terms of their implications for theories of spoken word recognition.