• 대한음성학회지:말소리
• /
• 제56호
• /
• pp.1-13
• /
• 2005

This study examined the speech intelligibility of one-syllable words with phonetic contrasts and analyzed segmental factors that can predict the overall speech intelligibility in hearing-impaired adults. To identify the speech error characteristics, a Korean word list was audio-recorded by 7 hearing-impaired adults, and 35 listeners selected the heard word out of 5 choices. Based in part on previous studies of speech of the hearing impaired, the word list consisted of monosyllabic consonant-vowel-consonant (CVC) real word pairs. Stimulus words included 77 phonetic contrast pairs. The results showed that the percentage of errors in final position (coda) contrast was higher than in any other position in syllable. And the intelligibility deficit factors of phonetic contrast in the hearing-impaired were analyzed through stepwise regression analysis. The overall intelligibility was predicted by the error rate of manner contrast at coda, voicing contrast (homorganic triplets) at onset and high-low contrast at nucleus.

• 한국통신학회논문지
• /
• 제29권7C호
• /
• pp.962-970
• /
• 2004

본 논문에서는 TI사의 부동소수점 DSP인 TMS320C6701$^{TM}$을 이용한 2.4kbps EHSX(Enhanced Harmonic Stochastic Excitation) 음성부호화기의 실시간 구현 방법에 대해서 논한다. EHSX는 4khz의 대역폭을 갖는 음성신호를 2.4kbps의 비트율을 갖는 압축 패킷으로 변환하는 부호화 방법으로, 유/무성음에 따라 하모닉(Harmonic) 여기 부호화 방법과 CELP 부호화 방법을 선택적으로 사용하는 구조를 갖는다. 본 논문에서는 이러한 EHSX의 실시간 구현을 위해 연산량의 큰 비중을 차지하는 CELP 분석의 코드북 검색부분과 일부 IIR 필터링 부분에 대한 고정소수점 변환 방법과, 부호화시 하모닉 검색 및 피치 검색방법에 대한 알고리즘 상 연산량 감소 방법, DSP의 구조를 고려한 코드를 배치방법 등 연산량을 감소시키기 위한 최적화 방법을 제시한다. 설계된 음성 부호화기는 PESQ(perceptual evaluation of speech quality) ITU-T Recommendation P.862를 이용한 음질 평가 결과로서 약MOS 3.28을 얻었으며, 실시간으로 압축 및 복원을 수행한다.

• 음성과학
• /
• 제7권4호
• /
• pp.83-90
• /
• 2000

The purpose of this study was to examine some acoustic characteristics in the ear canal. It was assumed that a sound outside the external auditory canal could be different from the sound inside the external auditory canal. The acoustic signals were captured by a probe microphone placed at a distance within 1 cm from the tympanic membrane, and a reference microphone was placed over the upper pinna. Three vowels /a/, /i/, /u/ were recorded from a normal adult male speaker. The parameters such as the formant frequency ($Fl\simF5$) and the peak intensity were measured using a speech analyser, PCquirer. It was found that the entering part of the external auditory canal functions as a narrowing point as to the speech that passes through the free field. Results show that acoustic characteristics were changed for speech discrimination rather than speech perception.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1993년도 춘계학술대회
• /
• pp.113-115
• /
• 1993

In this paper, we proposed a speech support system of personal computer for the blind. The system is consist of hardware part and software part. The hardware part are consist of personal computer and sound card. The software part are consist of sound driver system, character table and sound output algorithm. This system can recognize inputted characters from keyboard and program produced character strings.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제13권6호
• /
• pp.427-431
• /
• 2007

본 논문에서는 어절별 중의성 해소 규칙과 trigram 통계 정보를 이용하는 혼합형 한국어 품사 태깅 시스템에 대하여 기술한다. 어절별 중의성 해소 규칙은 중의성을 가지는 어절들 각각에 대해 정의된 중의성 해소 규칙으로, 현재 중의성을 가지는 어절의 50%에 대해 작성되어 있다. 본 논문의 태깅 시스템은 먼저 보조용언, 숙어, 관용적 표현 등에 해당하는 공통규칙을 적용하고, 그 후에 어절별 중의성 해소 규칙을 적용한다. 마지막으로 중의성이 해소되지 않은 어절은 각 어절을 중심으로 하는 trigram 통계 정보를 이용하여 중의성을 해소한다. 실험 결과는 본 논문에서 제안하는 어절별 중의성 해소 규칙과 trigram 통계 정보를 혼합하여 중의성을 해소 시키는 방법이 높은 정확률과 넓은 처리 범위를 가지고 있다는 것을 보여준다.

• 대한전자공학회논문지SP
• /
• 제42권4호
• /
• pp.103-110
• /
• 2005

음성 데이터베이스는 TTS 시스템에서 가장 중요한 요소 중의 하나이다. 특히, 내장형 TTS 시스템에서는 서버형 TTS 시스템에서보다 좀 더 작은 데이터베이스를 필요로 한다. 이러한 이유로, 음성합성 데이터의 압축과 통계적 축소과정의 비중은 내장형 TTS 시스템에서 아주 중요한 항목이라고 말할 수 있다. 그러나 이러한 압축과 통계적 축소과정은 합성음질의 저하를 유발시킨다. 본 논문에서는 고품질 내장형 TTS 시스템에서의 데이터 구축방법을 제안하며, MOS 테스트를 통한 합성음질을 검증한다.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.245-253
• /
• 2022

Commenced in 1954 by IBM, machine translation has expanded immensely, particularly in this period. Machine translation can be broken into seven main steps namely- token generation, analyzing morphology, lexeme, tagging Part of Speech, chunking, parsing, and disambiguation in words. Morphological analysis plays a major role when translating Indian languages to develop accurate parts of speech taggers and word sense. The paper presents various machine translation methods used by different researchers for Indian languages along with their performance and drawbacks. Further, the paper concentrates on parts of speech (POS) tagging in Marathi dialect using various methods such as rule-based tagging, unigram, bigram, and more. After careful study, it is concluded that for machine translation, parts of speech tagging is a major step. Also, for the Marathi language, the Hidden Markov Model gives the best results for parts of speech tagging with an accuracy of 93% which can be further improved according to the dataset.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• 제18권4E호
• /
• pp.26-30
• /
• 1999

This paper introduces a prosodic phrasing method in Korean to improve the naturalness of speech synthesis, especially in text-to-speech conversion. In prosodic phrasing, it is necessary to understand the structure of a sentence through a language processing procedure, such as part-of-speech (POS) tagging and parsing, since syntactic structure correlates better with the prosodic structure of speech than with other factors. In this paper, the prosodic phrasing procedure is treated from two perspectives: dependency parsing and prosodic phrasing using dependency relations. This is appropriate for Ural-Altaic, since a prosodic boundary in speech usually concurs with a governor of dependency relation. From experimental results, using the proposed method achieved 12% improvement in prosody boundary prediction accuracy with a speech corpus consisting 300 sentences uttered by 3 speakers.

• 음성과학
• /
• 제10권4호
• /
• pp.167-177
• /
• 2003

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