• 말소리와 음성과학
• /
• 제10권1호
• /
• 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.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.241-248
• /
• 2007

In this paper, we propose a Transformation-Based Learning (TBL) method on generating the Korean standard pronunciation. Previous studies on the phonological processing have been focused on the phonological rule applications and the finite state automata (Johnson 1984; Kaplan and Kay 1994; Koskenniemi 1983; Bird 1995). In case of Korean computational phonology, some former researches have approached the phonological rule based pronunciation generation system (Lee et al. 2005; Lee 1998). This study suggests a corpus-based and data-oriented rule learning method on generating Korean standard pronunciation. In order to substituting rule-based generation with corpus-based one, an aligned corpus between an input and its pronunciation counterpart has been devised. We conducted an experiment on generating the standard pronunciation with the TBL algorithm, based on this aligned corpus.

• 대한음성학회지:말소리
• /
• 제48호
• /
• pp.57-67
• /
• 2003

This paper presents a systematic description of exceptional pronunciations for automatic Korean pronunciation generation. An automatic pronunciation generator in Korean is an essential part of a Korean speech recognition system and a TTS (Text-To-Speech) system. It is composed of a set of regular rules and an exceptional pronunciation dictionary. The exceptional pronunciation dictionary is created by extracting the words that have exceptional pronunciations, based on the characteristics of the words of exceptional pronunciation through phonological research and the systematic analysis of the entries of Korean dictionaries. Thus, the method contributes to improve performance of automatic pronunciation generator in Korean as well as the performance of speech recognition system and TTS system in Korean.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2002년도 11월 학술대회지
• /
• pp.41-44
• /
• 2002

This paper is related to the enhancement of speech recognition rate using enhanced pronunciation dictionary. Modern large vocabulary, continuous speech recognition systems have pronunciation dictionaries. A pronunciation dictionary provides pronunciation information for each word in the vocabulary in phonemic units, which are modeled in detail by the acoustic models. But in most speech recognition system based on Hidden Markov Model, actual pronunciation variations are disregarded. Without the pronunciation variations in the speech recognition system, the phonetic transcriptions in the dictionary do not match the actual occurrences in the database. In this paper, we proposed the unvoiced rule of semivowel in allophone rules to pronunciation dictionary. Experimental results on speech recognition system give higher performance than existing pronunciation dictionaries.

• 대한음성학회지:말소리
• /
• 제49호
• /
• pp.1-30
• /
• 2004

Although Standard Korean is based on Seoul Korean, the phonetic realization of syllable codas in Seoul Korean has not been satisfactorily investigated. This paper aims to study how Seoul speakers pronounce syllable codas in certain phonetic contexts and what pronunciation they prefer among variants. It is noted that the realization of a syllable coda is different word by word and generation by generation. It is also noted that the syllable coda of a word is realized differently depending on the following vowel. And we discussed how the Principles of Standard Korean Pronunciation should be revised in the future, based on the results of this study.

• 말소리와 음성과학
• /
• 제1권2호
• /
• pp.151-162
• /
• 2009

This paper aims to investigate how tensification preference has changed over time and discuss how appropriately tensification preference is reflected in Principles of Standard Pronunciation and Standard Korean Language Dictionary. For this research, a questionnaire survey of tensification preference was conducted. 173 test words were used and 156 native Seoul speakers participated in this survey. The results have shown that tensification preference has gradually increased from older to younger generations. In addition, Principles of Standard Pronunciation and Standard Korean Language Dictionary do not reflect real pronunciation appropriately. Therefore, some ways of incorporating the actual pronunciation of Seoul speakers in the Principles of Standard Pronunciation and the Standard Korean Language Dictionary are suggested.

• 한국음향학회지
• /
• 제23권3호
• /
• pp.248-252
• /
• 2004

실제 언어생활에 있어서 여러 다양한 경제적 문화적 사회적 환경에 따라 다른 어휘가 사용되고, 각각의 다양한 환경에서 새롭게 신조어가 추가되는 등 어휘의 양적인 변화가 일어난다. 이러한 역동적인 언어 현실을 자동 발음열 생성기에 반영하기 위하여, 본 논문은 추가된 텍스트로부터 예외발음사전을 구축하는 방법을 제안하고, 이러한 방법으로 구축된 예외발음사전을 이용한 자동 발음열 생성 시스템의 성능을 실험하였다. 본 시스템에 대하여 ETRI에서 출시된 음성인식용 텍스트 코퍼스 가운데 한 달 동안의 신문기사를 모은 53,750문장 (740,497 어절)을 이용하여 실험한 결과 100%의 성능을 얻었다.

• 한국음향학회지
• /
• 제20권2호
• /
• pp.35-43
• /
• 2001

음성 인식이나 음성 합성시 필요한 발음열을 수작업으로 작성할 경우 작성자의 음운변화 현상에 대한 전문적 언어지식을 비롯하여 많은 시간과 노력이 요구되며 일관성을 유지하기도 쉽지 않다. 또한 한국어의 음운 변화 현상은 단일 형태소의 내부와 복합어에서 결합된 형태소의 경계점, 여러 형태소가 결합해서 한 어절을 이룰 경우 그 어절 내부의 형태소의 경계점, 여러 어절이 한 어절을 이룰 때 구성 어절의 경계점에서 서로 다른 적용 양상을 보인다. 본 논문에서는 이러한 문제를 해결하기 위해서 형태음운론적 분석에 기반하여 문자열을 자동으로 발음열로 변환하는 발음 생성 시스템을 제안하였다. 이 시스템은 한국어에서 빈번하게 발생하는 음운변화 현상의 분석을 통해 정의된 음소 변동 규칙과 변이음 규칙을 다단계로 적용하여 가능한 모든 발음열을 생성한다. 각 음운변화 규칙을 포함하는 대표적인 언절 리스트를 이용하여 구성된 시스템의 안정성을 검증하였고, 발음사전 구성과 학습용 발음열의 유용성을 인식 실험을 통해 평가하였다. 그 결과 표제어 사이의 음운변화 현상을 반영한 발음사전의 경우 5-6％ 정도 나은 단어 인식률을 얻었으며, 생성된 발음열을 학습에 사용한 경우에서도 향상된 결과를 얻을 수 있었다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2002년도 11월 학술대회지
• /
• pp.81-85
• /
• 2002

We present a statistical analysis of Korean phonological variations using automatic generation of phonetic transcription. We have constructed the automatic generation system of Korean pronunciation variants by applying rules modeling obligatory and optional phonemic changes and allophonic changes. These rules are derived from knowledge-based morphophonological analysis and government standard pronunciation rules. This system is optimized for continuous speech recognition by generating phonetic transcriptions for training and constructing a pronunciation dictionary for recognition. In this paper, we describe Korean phonological variations by analyzing the statistics of phonemic change rule applications for the 60,000 sentences in the Samsung PBS(Phonetic Balanced Sentence) Speech DB. Our results show that the most frequently happening obligatory phonemic variations are in the order of liaison, tensification, aspirationalization, and nasalization of obstruent, and that the most frequently happening optional phonemic variations are in the order of initial consonant h-deletion, insertion of final consonant with the same place of articulation as the next consonants, and deletion of final consonant with the same place of articulation as the next consonants. These statistics can be used for improving the performance of speech recognition systems.

• International journal of advanced smart convergence
• /
• 제6권2호
• /
• pp.59-64
• /
• 2017

There are three sorts of voices of female vocalists: soprano, mezzo-soprano, and contralto according to the transliteration. Among them, the soprano has the highest vocal range. Since the voice is generated through the human vocal tract based on the voice generation model, it is greatly influenced by the vocal tract. The structure of vocal organs differs from person to person, and the formants characteristic of vocalization differ accordingly. The formant characteristic refers to a characteristic in which a specific frequency band appears distinctly due to resonance occurring in each vocal tract in the vocal process. Formant characteristics include personality that occurs in the throat, jaw, lips, and teeth, as well as phonological properties of phonemes. The first formant is the throat, the second formant is the jaw, the third formant and the fourth formant are caused by the resonance phenomenon in the lips and the teeth. Among them, pronunciation is influenced not only by phonological information but also by jaws, lips and teeth. When the mouth is small or the jaw is stiff when pronouncing, pronunciation becomes unclear. Therefore, the higher the accuracy of the pronunciation characteristics, the more clearly the formant characteristics appear in the grammar spectrum. However, many soprano singers can not open their mouths because their jaws, lips, teeth, and facial muscles are rigid to maintain high tones when singing, which makes the pronunciation unclear and thus the formant characteristics become unclear. In this paper, in order to confirm the accuracy of the pronunciation characteristics of soprano singers, the experimental group was selected as the soprano singers A, B, C, D, E of Korea and analyzed the grammar spectrum and conducted the MOS test for pronunciation recognition. As a result, soprano singer B showed a clear recognition from F1 to F5 and MOS test result showed the highest recognition rate with 4.6 points. Soprano singers A, C, and D appear from F1 to F3, but it was difficult to find formants above 2kHz. Finally, the soprano singer E had difficulty in finding the formant as a whole, and MOS test showed the lowest recognition rate at 2.1 points. Therefore, we confirmed that the soprano singer B, which exhibits the most distinct formant characteristics in the grammar spectrum, has the best pronunciation accuracy.