• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.5
• /
• pp.111-116
• /
• 2016

According to the Ministry of Science, ICT and Future Planning's survey of information gap, smartphone retention rate of disabled people stayed in one-third of non-disabled people, the situation is significantly less access to information for people with disabilities than non-disabled people. In this paper, we develop an application, CallHelper, that helps to be more convenient to use mobile voice calls to the auditory disabled people. CallHelper runs automatically when a call comes in, translates caller's voice to text output on the mobile screen, and displays the emotion reasoning from the caller's voice to visualize emoticons. It also saves voice, translated text, and emotion data that can be played back.

• MALSORI
• /
• no.31_32
• /
• pp.51-82
• /
• 1996

The purpose of this paper is to gather pairs of heteronyms in Modem Korean and to propose that all of them should be differentiated in both the Hanngul orthography and Romanization as well as in the IPA transcription. More than a quarter of the whole Korean vocabulary consists of words with a long vowel and the number of minimal pairs distinguished only by the chroneme reaches nearly ten thousand (ie. twenty thousand words). It is suggested here that the letter s in Hanngul and the letter 'h' in the Roman alphabet be used to represent the long vowel. Another factor which brings forth lots of heteronyms in Korean is the lacking of enough indication as to non-automatic reinforcement in the initial consonant o( a word (or a morpheme) when following another within a phrase (or a word). It is proposed here that the non-automatincally rienforced word-initial consonant should be written with the letter h (like ㅺ, ㅼ, ㅽ, ㅾ) and an apostrophe (like 물'새 or 밭'이랑, 물'약) in Hanngul, and with the letter c and an apostrophe (like c'g-, c'd-, c'b-, c'j- ) in the Roman alphabet The morpheme-initial reinforced consonant within a word is written with the letters k, 1, p and cz for ㅺ, ㅼ, ㅽ, and ㅾ respectively. The contrasted pronunciations of pairs of heteronyms beginning with ㅁ/m sound are transcribed here for exemplification in the IPA, Roman alphabet and Hanngul.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.3
• /
• pp.519-524
• /
• 2021

Recently, the fourth industrial revolution has become an area of interest to many countries, mainly in major advanced countries. Artificial intelligence technology, the core technology of the fourth industrial revolution, is developing in a form of convergence in various fields and has a lot of influence on the edutech field to change education innovatively. This paper builds an experimental environment using the DTW speech recognition algorithm and deep learning on various native and non-native data. Furthermore, through comparisons with CNN algorithms, we study non-native speakers to correct them with similar pronunciation to native speakers by measuring the similarity of English pronunciation.

• MALSORI
• /
• no.43
• /
• pp.151-161
• /
• 2002

This study presents performance analysis results of speaker adaptation for keyword spotting system. In this paper, we implemented MLLR (Maximum Likelihood Linear Regression) method on our middle size vocabulary keyword spotting system. This system was developed for directory services of universities and colleges. The experimental results show that speaker adaptation reduces the false alarm rate to 1/3 with the preservation of the mis-detection ratio. This improvement is achieved when speaker adaptation is applied to not only keyword models but also non-keyword models.

• MALSORI
• /
• no.50
• /
• pp.111-122
• /
• 2004

Automatic detection of laryngeal diseases by voice is attractive because of its non-intrusive nature. Cepstrum based approach to detect laryngeal cancer shows reliable performance even when the periodicity of voice signals is severely lost, but it has a drawback that it is not robust to channel mismatch due to different microphone characteristics. In this paper, to deal with mismatched training and test microphone conditions, we investigate channel compensation techniques such as Cepstral Mean Subtraction (CMS) and Pole Filtered CMS (PFCMS). According to our experiments, PFCMS yields better performance than CMS. By using PFCMS, we obtained 12% and 40% error reduction over baseline and CMS, respectively.

• MALSORI
• /
• no.46
• /
• pp.13-24
• /
• 2003

This experimental study shows that, in reading of the English isolated words that are enumerated, the releasing of the word-final stop is employed for signaling enumeration in company with the well-known intonational pattern for it. Furthermore, this study tries to find the aspects of the releasing of the stops in the word-final positions, focusing on the association of the stop releasing/nonreleasing with i) the POA (Place of Articulation) distinction of the word-final stop, ii) the various qualities of the vowel before the final stop, and iii) the voice distinction of the stop in the word-final position.

• MALSORI
• /
• no.33_34
• /
• pp.111-125
• /
• 1997

This experimental phonetic analysis aims to describe standard Korean simple vowels with a view to presenting the vowel quality change from generation to generation, especially between the 50's and the 20's. This change reflects that the contemporary vowel system has both stable and unstable aspect: the former can be affirmed in the vowels with extreme positions in the vowel quadrilateral. and the latter in some vowels(e.g.,'ㅔ/ㅐ') which have the non-quantal vowel characteristics in the current vowel system. Formant values are measured to show these. And the results of acoustic analysis are presented graphically in the vowel quadrilateral for the convenience' sake. The comparison between the articulatory vowel quadrilateral and the acoustic one shows a lot concerning the current vowel quality change.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.273.2-277
• /
• 1998

본 논문에서는 음소단위 비정형 연결합성 시, 접합점에서 포만트 불연속을 최소화할 수 있도록 이웃음소간 경계강도 예측모델과 합성단위 검색시 음소단위 최장일치 검색 알고리즘을 설계하였다. 합성단위 연결부에서 발생하는 신호왜곡을 최소화하기 위해 “_C_”환경에서 자음이 유성음화된 경우, “_V_”환경에서 모음이 무성음화된 경우, 그리고 유성음 사이의 포만트 주파수 차이에 대한 모델을 생성하여, 음소간의 조음강도가 약한 부분이 합성단위 경계로 설정되도록 하였다. 합성단위 경계가 결정되면 주어진 문장의 문맥정보만을 이용하여 코포스로부터 후보를 선택한다. 선택된 후보를 사이의 연결성을 측정하기 위하여 합성 경계를 기준으로 전, 후 음소에 대한 음성적 특성과 포만트 천이 특성을 고려하였다. 실험은 K-ToBI 레이블링된 200문장을 기반으로 하였으며, 코퍼스로부터 한 문장을 선택하여 이를 목적치 패턴으로 선정 한 후, 목적치 패턴과 후보사이의 단위비용과 후보들 간의 연결비용을 계산하여 최적의 합성단위열을 추출하는 방식으로 이루어졌다. 본 논문에서는 이러한 문맥종속 단위 기반의 합성단위 추출 알고리즘과 실험 결과에 대해 보고한다.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.19-22
• /
• 1998

In this study, the efficient channel coding method combined with CS-ACELP is proposed. The same convolutional coder and Viterbi decoder of COMA mobile communication system is used as channel coder. To make the best available use of limited channel coding redundancy, unequal error protection of punctured convolutional coder is used for variable reate allocation. But, the overall code rate is given by 2. The performance of proposed coder is analyzed and simulated in a Rayleigh fading channel. Experimental results show that the objective and subjective speech quality of variable rate channel coding methods are superior to those of non-variable channel coding method.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.1E
• /
• pp.73-78
• /
• 1992

시벼형 신호인 음성 신호의 분석에 칼만필터를 이용하였다. 일반적인 음성 분석은 프레임단위의 처리방법인 선형 예측 부호화 기법을 주로 이용하지만 음성의 시변 특성을 파악하는데에는 적절하지 못 하다. 따라서 순차적인 추정기법으로 많이 이용되는 칼만 필터를 음성 분석에 적용하였다. 또한 음성과 같은 시변신호에서는 과거 신호의 잡음의 분산값에 적당한 가중치를 부가하므로써 과거의 신호에 의해 서 현재의 추정값에 미치는 영향을 줄였으며 이를 음성의 천이 구간에서의 파라메타 추정에 사용하였 다. 그리고 음성신호 모델에서 생기는 모델링 오차는 일반적으로 백색 가우시안 잡음으로 가정하고 있 으나 이는 자음과 같은 무성음에서 특징 파라메타 푸정에는 오차가 적지만 모음등의 유성음에서는 음성 발생시의 여기신호인 펄스열에 의해서 많은 모델링 오차를 생기게 한다. 따라서 모델링 오차신호는 Non-Gaussian 확률분포로 가정한 후 로버스트 칼만 필터를 사용하여 합성으멩 대해 특징 파라메터를 추출하였다.