• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.47-50
• /
• 2002

This paper is to introduce 'Dr. Speaking', which was recently developed by Eonon Inc.. 'Dr. Speaking' is an English pronunciation tutoring system. This has three distinguishing features. First, it teaches how to organize a speaker's vocal organs to pronounce accurately. Second, after it compares a speaker's pronunciation with that of a native speaker's, it grades that speaker's pronunciation level according to phonetic standards. Third, it provides proper information necessary for correcting a speaker's incorrect pronunciation. It is not always easy for a tutoring system to execute the above three almost simutaneously. However, 'Dr. Speaking' proved itself that it is possible by adding speech technology (e.g. speech recognition) to phonetic knowledge.

• Speech Sciences
• /
• v.1
• /
• pp.39-53
• /
• 1997

As the segmental phonetic output is derived from its underlying form, the phonetic surface of intonation could also be derived from its underlying tone melody. In order to show clearly the phonological processes (in fact, we need more than just phonological processes) involved in the generation of intonational surface, we need to formalize the description of those processes. This paper firstly examines different types of sentence-final intonation contour in Korean, and then attempt to formalize the intonational behavior of those contours. In this attempt, we will investigate what kinds of linguistic information participate in deciding the shapes of the. contours and what kinds of tonological processes the underlying tone melody undergoes before it takes the surface shape. In this analysis of intonation contours, we focus on the linguistic structure rather than the acoustic property, adopting just two tones L and H as phonological tones, with four phonetic pitches.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• pp.193-198
• /
• 2005

The aim of this paper is to exam why the nouns that used /kh, ph, ts, th/, as the final phoneme changed. Assuming that these change related to the aspects of the word usage, we collected the word frequency and the phonetic form of words. The results are as follows : ① The realization of standard phonetic form is related to the frequency of case marker that could not be omitted, combined with the word. ② The changing into /s/ in a coronal consonant is related to the case marker [i].

• Proceedings of the KSPS conference
• /
• 2004.05a
• /
• pp.139-142
• /
• 2004

This study examines the acoustic characteristics of Korean stops of two dialect, Seoul and Daegu, 20 speakers of these two dialects were asked to read 15 words containing the stops of different places of articulation and phonation types at initial. The stops in the two dialects show mainly two acoustic differences. Firstly, There was a difference in distinctive features for phonetic types in the two dialects. Secondly, lenis revel fortis`s characters in Daegu dialect.

• Proceedings of the KSPS conference
• /
• 2004.05a
• /
• pp.199-204
• /
• 2004

The purpose of this paper is to find prosodic characteristics in voice imitation. Speakers change various phonetic features in voice imitation. Speakers change their pitch ranges in the most cases. Especially, the pitch range is important for word conditions. And, as imitators change the voice, the average value of f0 is close to high frequence than low frequence or middle level.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1606-1609
• /
• 1987

Statistical information about spoken Korean was obtained. The data are the results of analyzing the Korean phonetic dictionary. This is one of the basic survey to make phoneme ballanced corpus of Korean Speech Data Base (KSDB).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.801-804
• /
• 2001

This article is concerned with automatic segmentation of two adjacent vowels for speech signals. All kinds of transition case of adjacent vowels can be characterized by spectrogram. Firstly the voiced-speech is extracted by the histogram analysis of vowel indicator which consists of wavelet low pass components. Secondly given phonetic transcription and transition pattern spectrogram, the voiced-speech portion which has consecutive vowels automatically segmented by the template matching. The cross-correlation function is adapted as a template matching method and the modified correlation coefficient is calculated for all frames. The largest value on the modified correlation coefficient series indicates the boundary of two consecutive vowel sounds. The experiment is performed for 154 vowel transition sets. The 154 spectrogram templates are gathered from 154 words(PRW Speech DB) and the 161 test words(PBW Speech DB) which are uttered by 5 speakers were tested. The experimental result shows the validity of the method.

• Speech Sciences
• /
• v.7 no.2
• /
• pp.37-50
• /
• 2000

This paper describes a test of everyday speech understanding ability, in which a listener's utilization of the context-situational information of speech is assessed, and is compared with the utilization of acoustic-phonetic information. The test items are sentences which are presented in a babble type of noise, and the listener response is the key word in the sentence. The key words are always two-syllabic nouns and the questioning sentences are added to obtain the responding key words. Two types of sentences are used. One is the high-predictable sentences for which the key word is somewhat predictable from the context. The other is the low-predictable sentences for which the key-word cannot be predicted from the context. Both types are included in six 40-item forms of the test, which are balanced for intelligibility, key-word familiarity and predictability, phonetic content, and length. Performance of normally hearing listeners shows significantly different functions for various signal-to-noise ratios. The potential applications of this test, particularly in the assessment of speech understanding ability in the hearing impaired, are discussed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.369-372
• /
• 2018

This paper suggests non-parallel-voice-conversion network conversing voice between unmapped voice pair as source voice and target voice. Conventional voice conversion researches used learning methods that minimize spectrogram's distance error. Not only these researches have some problem that is lost spectrogram resolution by methods averaging pixels. But also have used parallel data that is hard to collect. This research uses PPGs that is input voice's phonetic data and a GAN learning method to generate more clear voices. To evaluate the suggested method, we conduct MOS test with GMM based Model. We found that the performance is improved compared to the conventional methods.

• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.727-729
• /
• 1999

We have developed a realtime phonetic typewriter implemented on IBM PC with sound card based on Windows 95. In this system, analyzing of speech signal, learning of neural network, labeling of output neurons and visualizing of recognition results are performed on realtime. The developing environment for speech processing is established by adding various functions, such as editing, saving, loading of speech data and 3-D or gray level displaying of spectrogram. Recognition experimental using Korean phone had a 71.42% for 13 basic consonant and 90.01% for 7 basic vowel accuracy.