• Proceedings of the Korean Society for Language and Information Conference
• /
• 1996.02a
• /
• pp.297-306
• /
• 1996

A spontaneously spoken, natural Japanese discourse contains many instances of the so-called redundant interjections and of backchannel utterances. These expressions have not hitherto received much attention and few systematic analyses have been made. We show that these utterances are characterizable as discourse markers, and that they comprise a well-defined category, characterizable in a regular manner by their phonologico-prosodic properties. Our report is based on an experiment involving spontaneously spoken conversations, recorded in a laboratory environment and analyzed using digital devices. Prosodic patterns of discourse markers occurring in the recorded conversations have been analyzed. Several pitch patterns have been found that characterize the most frequently used Japanese discourse markers

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.1E
• /
• pp.27-31
• /
• 1999

Recent linguistic researches have brought into focus the relations between prosodic structures and syntactic, semantic or phonological structures. Most of them prove that prosodic information is available for understanding syntactic, semantic and discourse structures. But this result has not been integrated yet into recent Korean speech recognition or understanding systems. This study, as a part of integrating prosodic information into the speech recognition system, proposes an automatic detection technique of Korean accentual phrase boundaries by using one-stage DP, and the normalized pitch pattern. For making the normalized pitch pattern, this study proposes a method of modified normalization for Korean spoken language. For the experiment, this study employs 192 sentential speech data of 12 men's voice spoken in standard Korean, in which 720 accentual phrases are included, and 74.4% of the accentual phrase boundaries are correctly detected while 14.7% are the false detection rate.

• MALSORI
• /
• no.35_36
• /
• pp.189-209
• /
• 1998

This study discusses Korean speech database that has been designed and constructed for common use, especially focusing on designing a list of words or sentences that covers various phonological environments. As the results, PBW(Phonetically Balanced words) and PBS(Phonetically Balanced Sentences) was selected from balanced text corpus using maximum entropy method. And, implemented workbench for spoken language data acquisition is presented in this paper. The workbench consists of grapheme to phoneme converter, utterance list selection module, speech data editing module, multi-layer labelling module, and phoneme context search module.

• Korean Linguistics
• /
• v.71
• /
• pp.1-22
• /
• 2016

The early 20th century is a period of time when Korea confronted with the surging waves of modernization, and made a variety of internal reactions. The Korean language, not immune to the upheaval, also experienced new changes and gradually gained characteristics of today's Korean. Although scholars have not yet fully agreed upon the time division of Korean, Gabo reformation (1896) is usually considered to be the beginning of modern Korean. Thus, the early 20th century was also the beginning of modern Korean. Phonological, lexical, and grammatical characteristics of modern day Korean began to appear during this period of time. Phonologically, the 10 vowel system was established, glottal sounds and aspirated sounds increased, vowel harmony declined. Phenomena such as vowel raising, front-vowelization, monophthongization, and the word-initial rule appeared. Meanwhile, hangul-Chinese mix writing became common practice, and hangul-only writing also started to take place in narrative writing, and elements of spoken language began to reflect in written language. All those pointed to the unification of written and spoken language. Under the influence of modernization, a great amount of new words appeared. Especially, Japanese and other foreign words flooded in in great quantities. Grammatically, '-eos-(-엇-), -neun-(-는-), -ges-(-겟-)' trichotomy system of tenses was established, and hearer-oriented honorific system also formed a binary system of 'hasoseo(하소서), hasibsio(하십시오), hao(하오), hage(하게), haera(해라)' and 'hae (해), haeyo(해요)'. In word formation and sentence construction, the use of '-gi(-기)' became more frequent than '-eum(-음)', while '~geot(~것)' also significantly increased. In negative, causative and passive expressions, the use of long form, which has fewer restrictions than the short form, became more frequent. A tendency towards simplicity appeared. In the same vain, long and complex sentences with several clauses tend to be avoided. Instead, short simple sentences became more favorable. Korean linguistics scholars should pay closer attention to the modernization period, which includes the early 20th century. In order to fully understand today's Korean language, more thorough research on this immediately preceding period is necessary.

• Speech Sciences
• /
• v.9 no.1
• /
• pp.207-215
• /
• 2002

Perceptual evaluation of duration models of spoken Korean was carried out based on the Classification and Regression Tree (CART) model for text-to-speech conversion. A reference set of durations was produced by a commercial text-to-speech synthesis system for comparison. The duration model which was built in the previous research (Chung & Huckvale, 2001) was applied to a Korean language speech synthesis diphone database, 'Hanmal (HN 1.0)'. The synthetic speech produced by the CART duration model was preferred in the subjective preference test by a small margin and the synthetic speech from the commercial system was superior in the clarity test. In the course of preparing the experiment, a labeled database of spoken Korean with 670 sentences was constructed. As a result of the experiment, a trained duration model for speech synthesis was obtained. The 'Hanmal' diphone database for Korean speech synthesis was also developed as a by-product of the perceptual evaluation.

• Speech Sciences
• /
• v.12 no.3
• /
• pp.185-200
• /
• 2005

The objective of this study is to examine acoustic cues in spoken French for the assessment of pronunciation which is necessary to realization of the multimedia system. The corpus is composed of simple expressions which consist of the French phonological system include all phonemes. This experiment was made on 4 male and female French native speakers and on 20 Korean speakers, university students who had learned the French language more than two years. We analyzed the recorded data by using spectrograph and measured comparative features by the numerical values. First of all, we found the mean and the deviation of all phonemes, and then chose features which had high error frequency and great differences between French and Korean pronunciations. The selected data were simplified and compared among them. After we judged whether the problems of pronunciation in each Korean speaker were either the utterance mistake or the interference of mother tongue, in terms of articulatory and auditory aspects, we tried to find acoustic features as simplified as possible. From this experiment, we could extract acoustic cues for the construction of the French pronunciation training system.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.163-170
• /
• 1996

본 논문에서는 거절기능을 갖는 음성인식 시스템의 시험운용에 대해 소개하였다. 거절기능은 소음 단어에 의한 방식과 인식 결과를 확인하는 방식을 둘 다 병행 사용하여 구현하였다. 소음단어는 필러모델을 정의하여 구현하였으며 인식결과를 확인하기 위해서는 선형변별기를 사용하였다. 연구실에서 구축한 음성 DB로 HMM 파라미터를 추출한 후 시험운용 6개월 동안 구한 음성 DB로 실험한 결과 84.1%의 인식률을 구하였으며 이때 거절률은 0.8%였다.

• MALSORI
• /
• no.42
• /
• pp.37-46
• /
• 2001

Recently speech technologies have shown notable advancements and they now play major roles in computer-aided language learning systems. In the current paper, use of speech recognition technologies is viewed with our system for teaching English pronunciation to Japanese speakers.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.3
• /
• pp.357-362
• /
• 2004

Language models are essential in predicting the next word in a spoken sentence, thereby enhancing the speech recognition accuracy, among other things. However, spoken language domains are too numerous, and therefore developers suffer from the lack of corpora with sufficient sizes. This paper proposes a method of combining two n-gram language models, one constructed from a very small corpus of the right domain of interest, the other constructed from a large but less adequate corpus, resulting in a significantly enhanced language model. This method is based on the observation that a small corpus from the right domain has high quality n-grams but has serious sparseness problem, while a large corpus from a different domain has more n-gram statistics but incorrectly biased. With our approach, two n-gram statistics are combined by extending the idea of Katz's backoff and therefore is called a dual-source backoff. We ran experiments with 3-gram language models constructed from newspaper corpora of several million to tens of million words together with models from smaller broadcast news corpora. The target domain was broadcast news. We obtained significant improvement (30%) by incorporating a small corpus around one thirtieth size of the newspaper corpus.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2E
• /
• pp.43-50
• /
• 2009

To get more natural synthetic speech generated by a Korean TTS (Text-To-Speech) system, we have to know all the possible prosodic rules in Korean spoken language. We should find out these rules from linguistic, phonetic information or from real speech. In general, all of these rules should be integrated into a prosody-generation algorithm in a TTS system. But this algorithm cannot cover up all the possible prosodic rules in a language and it is not perfect, so the naturalness of synthesized speech cannot be as good as we expect. ANNs (Artificial Neural Networks) can be trained to learn the prosodic rules in Korean spoken language. To train and test ANNs, we need to prepare the prosodic patterns of all the phonemic segments in a prosodic corpus. A prosodic corpus will include meaningful sentences to represent all the possible prosodic rules. Sentences in the corpus were made by picking up a series of words from the list of PB (phonetically Balanced) isolated words. These sentences in the corpus were read by speakers, recorded, and collected as a speech database. By analyzing recorded real speech, we can extract prosodic pattern about each phoneme, and assign them as target and test patterns for ANNs. ANNs can learn the prosody from natural speech and generate prosodic patterns of the central phonemic segment in phoneme strings as output response of ANNs when phoneme strings of a sentence are given to ANNs as input stimuli.