• 음성과학
• /
• 제12권4호
• /
• pp.247-254
• /
• 2005

This study aimed at clarifing clinical effects of eight-step continuum treatment in a patient who showed apraxia of speech after stroke. The eight-step continuum treatment consisted of 8 steps and its clinical efficacy has been proven with American apraxic patients. However, it has not been clinically proven to be effective in Korean patients with apraxia of speech as of yet. Therefore, this study was conducted in an effort to provide preliminary clinical evidence regarding its effectiveness regardless of the linguistic differences between Korean and English. The therapy took place twice a week for 6 months, a total of 48 times. The results showed that the patient's receptive language was improved from 83% to 89% and 37% in accuracy, and expressive language from 15% to 37%. It seemed that spontaneous recovery did not playa role in his improvement since the study was conducted 2 years after the stroke. In addition, the improvement of expressive language was much greater(22%) than that of receptive language(6%), which implied that the therapy was effective in apraxia of speech because apraxia of speech is relatively confined to expressive ability, more specifically motor programming and sequencing.

• 한국정보컨버전스학회:학술대회논문집
• /
• 한국정보컨버전스학회 2008년도 International conference on information convergence
• /
• pp.53-56
• /
• 2008

This paper reports on the ACQA(Animated agent for Conversational Question Answering) project conducted at LIMSI. The aim is to design an expressive animated conversational agent(ACA) for conducting research along two main lines: 1/ perceptual experiments(eg perception of expressivity and 3D movements in both audio and visual channels): 2/ design of human-computer interfaces requiring head models at different resolutions and the integration of the talking head in virtual scenes. The target application of this expressive ACA is a real-time question and answer speech based system developed at LIMSI(RITEL). The architecture of the system is based on distributed modules exchanging messages through a network protocol. The main components of the system are: RITEL a question and answer system searching raw text, which is able to produce a text(the answer) and attitudinal information; this attitudinal information is then processed for delivering expressive tags; the text is converted into phoneme, viseme, and prosodic descriptions. Audio speech is generated by the LIMSI selection-concatenation text-to-speech engine. Visual speech is using MPEG4 keypoint-based animation, and is rendered in real-time by Virtual Choreographer (VirChor), a GPU-based 3D engine. Finally, visual and audio speech is played in a 3D audio and visual scene. The project also puts a lot of effort for realistic visual and audio 3D rendering. A new model of phoneme-dependant human radiation patterns is included in the speech synthesis system, so that the ACA can move in the virtual scene with realistic 3D visual and audio rendering.

• 대한음성학회지:말소리
• /
• 제63호
• /
• pp.101-112
• /
• 2007

Spoken dialog system development includes many laborious and inefficient tasks. Since there are many components such as speech recognition, language understanding, dialog management and knowledge management in a spoken dialog system, a developer should take an effort to edit corpus and train each model separately. To reduce a cost for editing corpus and training each model, we need more systematic and efficient working environment. For the working environment, we propose DialogStudio as a spoken dialog system workbench.

• 대한후두음성언어의학회지
• /
• 제27권1호
• /
• pp.18-20
• /
• 2016

Total laryngectomy remains as an important treatment option in selected patients with laryngopharyngeal cancers, which inevitably sacrifices naturally produced voice. Much effort has been devoted to voice restoration for these laryngectomized patients. Several ways of voice rehabilitation after total laryngectomy have been developed and utilized thus far, including tracheoesophageal shunt speech, esophageal speech, pneumatic speech aid, and electrolarynx. Of these, tracheoesophageal shunt speech appears to be the most effective voice restoration method, while other trials might also be useful in special situations. Nevertheless, each method has its own unique mechanisms of voice production, thus has its advantages and drawbacks in clinical setting. In this review, we discuss the currently available management options for the rehabilitation of laryngectomized voice.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 2월 학술대회지
• /
• pp.157-172
• /
• 1996

This study aims to suggest some theoretical methodology for analysis of the prosodic patterns in Korean Read Speech. The engineering effort relevant to the phonetic study has focused to the importance of prosodic phrasing which may play a major role in analyzing the phonetic DB. Before establishing the prosodic phrase as the prosodic unit, we should describe the features of the boundary signal in a target sentence. With this in mind, the general characteristics of Read Speech and the ToBI(tones and Break Indices), which has been currently in vogue with respect to the prosodic labelling system were presented as the first step. The concrete analysis was carried out with the fable 'North Wind and the Sun' Korean version, where about 25 prosodic units were discriminated by perceptual approach for 5 subjects. Establishing various informations which can be used for deciding a boundary position systematically, we can proceed to the next, viz. acoustic analysis of prosodic unit. The most important which we primarily study for improving the naturalness of synthetic speech may be, at first, detecting the boundary signals in the speech file and accordingly reestablishment it within the raw text.

• 한국전자통신학회논문지
• /
• 제5권4호
• /
• pp.363-371
• /
• 2010

특징벡터의 분류를 개선시켜 화자독립 음성인식의 오류율을 줄이려는 노력의 일환으로서, 우리는 MFCC의 추출에 있어서 푸리에 스펙트럼을 기울이는 방법이 미치는 효과를 연구한다. 음성신호에 FIR 필터링을 적용하는 효과의 조사도 병행된다. 제안된 방법은 두 가지 독립적인 방법에 의해 평가된다. 즉, 피셔의 차별함수에 의한 방법과 은닉 마코브 모델 및 퍼지 벡터양자화를 사용한 음성인식 오류율 조사 방법이다. 실험 결과, 적절한 파라미터의 선택에 의해 기존의 방법에 비해 10% 정도 낮은 인식 오류율이 얻어짐을 확인하였다.

• 말소리와 음성과학
• /
• 제13권4호
• /
• pp.67-74
• /
• 2021

본 연구는 영유아 교육시설에서 근무하는 음성의 불편감을 호소하는 10명의 여성 교사들을 대상으로 반폐쇄성도훈련(semi-occluded vocal tract exercise, SOVTE)을 원격으로 실시하였을 때 주관적으로 평가하는 음성평가에 미치는 효과를 살펴보았다. 원격 SOVTE의 효과는 한국어판 음성장애지수(Korean voice handicap index, KVHI), 음성 활동 및 참여 프로파일-한국판(Korean version of the voice activity and participation profile, K-VAPP), 음성노력도 및 GRBAS를 이용한 청지각적 평가로 평가하였다. 연구 결과, KVHI의 총 점수, 기능적 점수, 신체적 점수는 원격 SOVTE를 실시한 후에 통계적으로 유의하게 낮아졌다. 원격 SOVTE 실시 후 K-VAPP의 총 점수도 유의하게 감소하였으며, 음성노력도 또한 유의하게 감소하였다. 그러나 GRB 척도는 원격 SOVTE 실시 전과 후 간에 통계적으로 유의한 차이를 보이지 않았다. 본 연구를 통해 영유아 여성 교사에게 원격으로 실시한 SOVTE는 음성의 불편감을 감소시키는데 효과적임을 입증하였으며, 원격으로 실시한 음성치료가 효과가 있음을 보여준다.

• 한국전자통신학회논문지
• /
• 제5권6호
• /
• pp.568-574
• /
• 2010

음성인식에서의 인식률 향상을 위한 노력의 일환으로서, 본 논문에서는 성별을 구분하지 않는 일반적 화자독립 음성인식과 성별에 따른 음성인식의 성능을 비교하는 연구를 수행하였다. 실험을 위해 남녀 각 20명의 화자로 하여금 각각 300단어를 발성하게 하고, 그 음성 데이터를 여성/남성/혼성A/혼성B의 네 그룹으로 나누었다. 우선, 성별 음성인식에 대한 근거의 타당성을 파악하기 위하여 음성 신호의 주파수 분석 및 MFCC 특징벡터들의 성별 차이를 조사하였다. 그 결과, 성별 음성인식의 동기를 뒷받침할 정도의 두드러진 성별 차이가 확인되었다. 음성인식을 수행한 결과, 성을 구분하지 않는 일반적인 화자독립의 경우에 비해 성별 음성인식에서의 오류율이 절반 이하로 떨어지는 것으로 나타났다. 이로부터, 성 인식과 성별 음성인식을 계층적으로 수행함으로써 화자독립의 인식률을 높일 수 있을 것으로 사료된다.

• 한국정보통신학회논문지
• /
• 제7권6호
• /
• pp.1168-1176
• /
• 2003

인터넷 전화 서비스는 저렴한 가격과 타 서비스와 통합 및 가치부가면에서 기존의 전화에 비해 많은 장점을 가지고 있으나, 상대적으로 낮은 음질로 인하여 사용자의 요구를 만족시키지 못하고 있다. 이것은 인터넷이 best-effort형 패킷 전달 서비스만을 제공하고 있기 때문에 지연, 패킷 손실 및 지터 등을 보장할 수 없기 때문이다. 본 논문에서는 인터넷 전화에서 전송지연으로 인한 패킷손실을 감소시키기 위해 수신 패킷을 사람이 인지 가능한 수준까지 확장하여 playout 시킬 수 있는 FEAPT 알고리즘을 제시한다.

• Journal of Multimedia Information System
• /
• 제5권3호
• /
• pp.209-214
• /
• 2018

Today is the era of artificial intelligence. With the development of artificial intelligence, machines have begun to impersonate various human characteristics today. Chatbot is one instance of this interactive artificial intelligence. Chatbot is a computer program that enables to conduct natural conversations with people. As mentioned above, Chatbot conducted conversations in text, but Chatbot, in this study evolves to perform commands based on speech-recognition. In order for Chatbot to perfectly emulate a human dialogue, it is necessary to analyze the sentence correctly and extract appropriate response. To accomplish this, the sentence is classified into three types: objects, actions, and preferences. This study shows how objects is analyzed and processed, and also demonstrates the possibility of evolving from an elementary model to an advanced intelligent system. By this study, it will be evaluated that speech-recognition based Chatbot have improved order-processing time efficiency compared to text based Chatbot. Once this study is done, speech-recognition based Chatbot have the potential to automate customer service and reduce human effort.