• 영어영문학
• /
• 제57권3호
• /
• pp.457-472
• /
• 2011

The word "subject," like its apparent antonym "agent" is ambiguous. By "speaking subject" I intend both meanings: the spoken about, and the speaker, and the spoken about, in more or less that order. The paper contrasts the way women are spoken about in the 19^th Century debate over the role of women between John Ruskin and John Mill, and then in literary criticism of feminists nearer our own time, Kate Millet and Elizabeth Langland. I then move on to women as speaking subjects, first in the form of an imaginary speaking subject created by a male speaker, Charles Dickens channeling the confessional journal of Esther Summerson in Bleak House. The comparison with Elizabeth Gaskell, a genuine speaking subject, is highly instructive. I draw attention to symmetrical, in the sense of opposite, narrative strategies. Where Dickens begins in journalese, with a gritty, realistic opening that only gradually reveals a Cinderella in the ashes, Gaskell begins with a nursery rhyme, in an actual nursery, but goes on to reveal some rather sordid economic facts. Where Dickens creates a ventriloquist's doll, Gaskell succeeds in creating recognizable, if not always admirable, female voices. I conclude that just as the novel may be read as a real utterance in a real conversation, it is also possible to read the true emergence of women novelists in the 19^th Century as nothing more and nothing less than the creation of the first truly womanly words about women: women as speaking subjects in both senses of the word.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 1996년도 제8회 한글 및 한국어 정보처리 학술대회
• /
• pp.145-152
• /
• 1996

연속음성인식 시스템을 개발하기 위해서는 언어가 갖는 문법적 제약을 이용한 언어모델이 요구된다. 문법적 규칙을 이용한 언어모델은 전문가가 일일이 문법 규칙을 만들어 주어야 하는 단점이 있다. 통계적 언어 모델에서는 문법적인 정보를 수작업으로 만들어 주지 않는 대신 그러한 모든 정보를 학습을 통해서 훈련해야 하기 때문에 이를 위해 요구되는 학습 데이터도 엄청나게 증가한다. 따라서 적은 양의 데이터로도 이와 유사한 효과를 보일 수 있는 것이 클래스에 의거한 언어 모델이다. 또 이 모델은 음성 인식과 연계시에 탐색 공간을 줄여 주기 때문에 실시간 시스템 구현에 매우 유용한 모델이다. 여기서는 자동으로 클래스를 찾아주는 알고리즘을 호텔예약시스템의 corpus에 적용, 분석해 보았다. Corpus 자체가 문법규칙이 뚜렷한 특성을 갖고 있기 때문에 heuristic하게 클래스를 준 것과 유사한 결과를 보였지만 corpus 크기가 커질 경우에는 매우 유용할 것이며, initial map을 heuristic하게 주고 그 알고리즘을 적용한 결과 약간의 성능향상을 볼 수 있었다. 끝으로 음성인식시스템과 접합해 본 결과 유사한 결과를 얻었으며 언어모델에도 음향학적 특성을 반영할 수 있는 연구가 요구됨을 알 수 있었다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2014년도 제26회 한글 및 한국어 정보처리 학술대회
• /
• pp.3-8
• /
• 2014

대화형 개인 비서 시스템은 사람의 음성을 통해 인식된 음성 인식 결과를 분석하여 사용자에게 제공할 정보가 무엇인지 파악한 후, 정보가 포함되어 있는 앱(app)을 실행시켜 사용자가 원하는 정보를 제공하는 시스템이다. 이러한 대화형 개인 비서 시스템의 가장 중요한 모듈 중 하나는 음성 대화 인식 모듈(SLU: Spoken Language Understanding)이며, 발화의 "의미 분석"을 수행하는 모듈이다. 본 논문은 음성 인식결과가 잘못되어 의미 분석이 실패하는 것을 방지하기 위하여 음성 인식 결과에서 잘못 인식된 명사, 개체명 단어를 보정 시켜주는 미등록어(OOV:Out-of-vocabulary) 처리 모듈을 제안한다. 제안하는 미등록어 처리 모듈은 미등록어 탐색 모듈과 미등록어 변환 모듈로 구성되며, 미등록어 탐색 모듈을 통해 사용자의 발화에서 미등록어를 분류하고, 미등록어 변환 모듈을 통해 미등록어를 사전에 존재하는 유사한 단어로 변환하는 방법을 제안한다. 제안한 방법을 적용하였을 때의 실험 결과, 전체 미등록어 중 최대 52.5%가 올바르게 수정되었으며, 음성 인식 결과를 그대로 사용했을 경우 "원본 문장"과 문장 단위 67.6%의 일치율을 보인 것에 반해 미등록어 처리 모듈을 적용했을 때 17.4% 개선된 최대 85%의 문장 단위 일치율을 보였다.

• ETRI Journal
• /
• 제18권1호
• /
• pp.29-41
• /
• 1996

This paper describes a method to select a suitable feature for speech recognition using information theoretic measure. Conventional speech recognition systems heuristically choose a portion of frequency components, cepstrum, mel-cepstrum, energy, and their time differences of speech waveforms as their speech features. However, these systems never have good performance if the selected features are not suitable for speech recognition. Since the recognition rate is the only performance measure of speech recognition system, it is hard to judge how suitable the selected feature is. To solve this problem, it is essential to analyze the feature itself, and measure how good the feature itself is. Good speech features should contain all of the class-related information and as small amount of the class-irrelevant variation as possible. In this paper, we suggest a method to measure the class-related information and the amount of the class-irrelevant variation based on the Shannon's information theory. Using this method, we compare the mel-scaled FFT, cepstrum, mel-cepstrum, and wavelet features of the TIMIT speech data. The result shows that, among these features, the mel-scaled FFT is the best feature for speech recognition based on the proposed measure.

• 대한음성학회지:말소리
• /
• 제68권
• /
• pp.49-63
• /
• 2008

This paper describes the development and assessment of a hidden Markov model (HMM) based Tagalog speech synthesis system, where Tagalog is the most widely spoken indigenous language of the Philippines. Several aspects of the design process are discussed here. In order to build the synthesizer a speech database is recorded and phonetically segmented. The constructed speech corpus contains approximately 89 minutes of Tagalog speech organized in 596 spoken utterances. Furthermore, contextual information is determined. The quality of the synthesized speech is assessed by subjective tests employing 25 native Tagalog speakers as respondents. Experimental results show that the new system is able to obtain a 3.29 MOS which indicates that the developed system is able to produce highly intelligible neutral Tagalog speech with stable quality even when a small amount of speech data is used for HMM training.

• 한국정보통신설비학회:학술대회논문집
• /
• 한국정보통신설비학회 2002년도 하계학술대회 및 세미나
• /
• pp.213-219
• /
• 2002

본 논문은 상용 OS 인 windows CE 기반의 PDA에서 음성으로 각 응용 프로그램 을 실행하는 방법 및 구성을 제시한다. PDA는 기존 desktop PC 에 비해 사용자 입력수단이 많지 않고, 그 사용법조차 까다롭다. 예를 들어 SIP(Soft Input Panel)을 이용하여 채팅을 하거나 인터넷 웹 브라우저에 주소입력조차 쉽지 않다. 이에 KT의 자체 개발한 음성인식엔진을 이용하여 PDA내 응용프로그램 과 사용자입력 요구사항을 원활히 연결, 보다 편리한 사용자 입력인터페이스를 제공한다. KT의 음성인식엔진은 corpus 기반으로 HMM 모델을 이용, 사용자 음성을 인식하여 그 결과를 출력한다. 본 논문에서는 PDA에서의 이러한 음성인식엔진을 이용, 다수의 응용프로그램을 실행하고 제어하는 구성과 패턴을 제시한다.

• The Journal of the Acoustical Society of Korea
• /
• 제20권4E호
• /
• pp.31-38
• /
• 2001

A large-scale synthesis database for a unit selection based synthesis method usually retains redundant synthesis unit instances, which are useless to the synthetic speech quality. In this paper, to eliminate those instances from the synthesis database, we proposed a new pruning method called weighted vector quantization (WVQ). The WVQ reflects relative importance of each synthesis unit instance when clustering the similar instances using vector quantization (VQ) technique. The proposed method was compared with two conventional pruning methods through the objective and subjective evaluations of the synthetic speech quality: one to simply limit maximum number of instance, and the other based on normal VQ-based clustering. The proposed method showed the best performance under 50% reduction rates. Over 50% of reduction rates, the synthetic speech quality is not seriously but perceptibly degraded. Using the proposed method, the synthesis database can be efficiently reduced without serious degradation of the synthetic speech quality.

• 인문언어
• /
• 제8집
• /
• pp.79-93
• /
• 2006

The modern play is going through a change that is differentiating it from the plays of yesterday. The importance of narration through language, specifically that of words spoken on stage as a means of communication is being replaced by images and minimalism of words. The narration that depended on spoken words today depends more on the images that are conjured on stage. This movement shows also the very development of stage and its craft in the domain of theater and especially holds true in the avant-garde theaters of today. The avant-garde theater, in trying to duplicate the reality does not confine itself to oratory rhetorics that we see in the traditional plays of the past but expresses itself by mimicking the reality to the utmost possible.

• 음성과학
• /
• 제12권2호
• /
• pp.183-191
• /
• 2005

This paper describes the automated call routing for call center system based on speech recognition. We focus on the task of automatically routing telephone calls based on a users fluently spoken response instead of touch tone menus in an interactive voice response system. Vector based call routing algorithm is investigated and normalization method suggested. Call center database which was collected by KT is used for call routing experiment. Experimental results evaluating call-classification from transcribed speech are reported for that database. In case of small training data, an average call routing error reduction rate of 9% is observed when normalization method is used.

• The Journal of the Acoustical Society of Korea
• /
• 제16권1E호
• /
• pp.57-63
• /
• 1997

In this paper, we investigated performance of a vocabulary-independent speech recognizer with speaker adaptation. The vocabulary-independent speech recognizer does not require task-oriented speech databases to estimate HMM parameters, but adapts the parameters recursively by using input speech and recognition results. The recognizer has the advantage that it relieves efforts to record the speech databases and can be easily adapted to a new task and a new speaker with different recognition vocabulary without losing recognition accuracies. Experimental results showed that the vocabulary-independent speech recognizer with supervised offline speaker adaptation reduced 40% of recognition errors when 80 words from the same vocabulary as test data were used as adaptation data. The recognizer with unsupervised online speaker adaptation reduced abut 43% of recognition errors. This performance is comparable to that of a speaker-independent speech recognizer trained by a task-oriented speech database.