• 디지털융복합연구
• /
• 제11권1호
• /
• pp.225-236
• /
• 2013

음성인식 기술은 단순한 단어 인식을 넘어 자연스럽게 발성한 연속 음성도 인식할 수 있는 수준으로 발전해 왔다. 아이폰에 탑재된 자연어 음성인식 처리 소프트웨어인 시리(Siri)가 2010년에 발표되면서, 음성인식에 대한 연구가 관심을 받고 있다. 한국어 음성 인식 소프트웨어들은 대부분 단어 위주의 인식 서비스로 구성 되어 있으며, 잡음처리 및 음성 에너지 조절 기능들이 부족해 만족할 만한 인식률을 보이지 못하고 있다. 또한 요구된 발성 규칙을 따르지 못한 음성 질의들은 아예 처리하지 못하고 있는 실정이다. 본 논문에서는 이러한 현실적 어려움을 개선할 수 있도록 다목적 전처리 프로세서를 제안하였다. 이 처리기는 음성인식 엔진에 독립적이며, 잡음 제거 기능, 규칙에 따르지 않은 음성 질의도 처리 할 수 있는 핵심어 추출 기능, 그 핵심어를 수식하는 전술부 및 그 해당 음성 질의로부터 수행하기를 원하는 후술부 까지도 추출할 수 있는 기능을 갖추도록 하였다. 실험을 통해, 잡음 제거 효과 평가, 핵심어 인식 성공률, 연속음 인식 성공률을 측정하여 제안한 방법의 타당성을 확인하였다.

• 한국음향학회지
• /
• 제14권5호
• /
• pp.44-50
• /
• 1995

본 논문에서는 연속분포 HMM을 이용한 대용량 한국어 연속음성인식 시스템에 관하여 기술한다. 인식 시스템의 성능을 개선하기 위하여 음성 모델링 단위의 선정, 단어간 모델링, 탐색 알고리듬, 문법에 관하여 연구하였다. 기본 인식단위로 트라이존을 사용하며 학습성을 개선하고 기능어에서의 에러 발생을 줄이기 위하여 일반화된 트라이폰과 function word-de-pendent phone을 사용한다. 단어 사이에는 묵음 모델과 null transition을 사용하여 선택적으로 묵음을 추가하였다. 언어모델로는 단어 클래스에 근거한 word pair 문법과 bigram 모델이 이용된다. 또한 지식 정보들을 효율적으로 활용할 수 있도록 N개의 후보 문장들을 탐색할 수 있는 알고리듬을 구현하였다. 후처리기에서는 word triple문법을 사용하여 N개의 최적 문장을 재정렬하여 최종적인 인식 문장을 결정하며, 마지막으로 후치사와 관련된 사소한 에러들을 수정한다. 3천단어의 연속음성 데이타베이스에 대한 인식실험에서, 후처리로 word triple 문법을 사용하여 $93.1\%$의 단어 인식률과 $73.8\%$의 문장 인식률을 얻었다.

• 전자공학회논문지B
• /
• 제28B권7호
• /
• pp.548-556
• /
• 1991

In this paper, Korean spoken continuous digits are ercognized using DHMM(Dynamic Hidden Markov Model) and lexical analysis to provide the base of developing voice dialing system. After segmentation by phoneme unit, it is recognized. This system can be divided into the segmentation section, the design of standard speech section, the recognition section, and the lexical analysis section. In the segmentation section, it is segmented using the ZCR, O order LPC cepstrum, and Ai, parameter of voice speech dectaction, which is changed according to time. In the standard speech design section, 19 phonemes or syllables are trained by DHMM and designed as a standard speech. In the recognition section, phomeme stream are recognized by the Viterbi algorithm.In the lexical decoder section, finally recognized continuous digits are outputed. This experiment shiwed the recognition rate of 85.1% using data spoken 7 times of 21 classes of 7 continuous digits which are combinated all of the occurence, spoken by 10 man.

• 대한음성학회지:말소리
• /
• 제59호
• /
• pp.53-68
• /
• 2006

We report the evaluation results of the Korean speech recognition platform called ECHOS. The platform has an object-oriented and reusable architecture so that researchers can easily evaluate their own algorithms. The platform has all intrinsic modules to build a large vocabulary speech recognizer: Noise reduction, end-point detection, feature extraction, hidden Markov model (HMM)-based acoustic modeling, cross-word modeling, n-gram language modeling, n-best search, word graph generation, and Korean-specific language processing. The platform supports both lexical search trees and finite-state networks. It performs word-dependent n-best search with bigram in the forward search stage, and rescores the lattice with trigram in the backward stage. In an 8000-word continuous speech recognition task, the platform with a lexical tree increases 40% of word errors but decreases 50% of recognition time compared to the HTK platform with flat lexicon. ECHOS reduces 40% of recognition errors through incorporation of cross-word modeling. With the number of Gaussian mixtures increasing to 16, it yields word accuracy comparable to the previous lexical tree-based platform, Julius.

• 대한음성학회지:말소리
• /
• 제57호
• /
• pp.153-164
• /
• 2006

The MMSE-STSA based speech enhancement algorithm is widely used as a preprocessing for noise robust speech recognition. It weighs the gain of each spectral bin of the noisy speech using the estimate of noise and signal power spectrum. In this paper, we investigate the influence of parameters used to estimate the speech signal and noise power in MMSE-STSA upon the recognition performance of noisy speech. For experiments, we use the Aurora2 DB which contains noisy speech with subway, babble, car, and exhibition noises. The HTK-based continuous HMM system is constructed for recognition experiments. Experimental results are presented and discussed with our findings.

• The Journal of the Acoustical Society of Korea
• /
• 제15권4E호
• /
• pp.21-27
• /
• 1996

In this paper, we propose a discriminative training algorithm for the stochastic segment model (SSM) in continuous speech recognition. As the SSM is usually trained by maximum likelihood estimation (MLE), a discriminative training algorithm is required to improve the recognition performance. Since the SSM does not assume the conditional independence of observation sequence as is done in hidden Markov models (HMMs), the search space for decoding an unknown input utterance is increased considerably. To reduce the computational complexity and starch space amount in an iterative training algorithm for discriminative SSMs, a hybrid architecture of SSMs and HMMs is programming using HMMs. Given the segment boundaries, the parameters of the SSM are discriminatively trained by the minimum error classification criterion based on a generalized probabilistic descent (GPD) method. With the discriminative training of the SSM, the word error rate is reduced by 17% compared with the MLE-trained SSM in speaker-independent continuous speech recognition.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1705-1709
• /
• 2005

This paper covers review and challenges in the area of speech recognition by taking into account different classes of recognition mode. The recognition mode can be either speaker independent or speaker dependant. Size of the vocabulary and the input mode are two crucial factors for a speech recognizer. The input mode refers to continuous or isolated speech recognition system and the vocabulary size can be small less than hundred words or large less than few thousands words. This varies according to system design and objectives.[2]. The organization of the paper is: first it covers various fundamental methods of speech recognition, then it takes into account various deficiencies in the existing systems and finally it discloses the various probable application areas.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권11호
• /
• pp.2800-2812
• /
• 2012

The purpose of this study was to examine the syllable-word boundary misalignment cost on word segmentation in Korean continuous speech. Previous studies have demonstrated the important role of syllabification in speech segmentation. The current study investigated whether the resyllabification process affects word recognition in Korean continuous speech. In Experiment I, under the misalignment condition, participants were presented with stimuli in which a word-final consonant became the onset of the next syllable. (e.g., /k/ in belsak ingan becomes the onset of the first syllable of ingan 'human'). In the alignment condition, they heard stimuli in which a word-final vowel was also the final segment of the syllable (e.g., /eo/ in heulmeo ingan is the end of both the syllable and word). The results showed that word recognition was faster and more accurate in the alignment condition. Experiment II aimed to confirm that the results of Experiment I were attributable to the resyllabification process, by comparing only the target words from each condition. The results of Experiment II supported the findings of Experiment I. Therefore, based on the current study, we confirmed that Korean, a syllable-timed language, has a misalignment cost of resyllabification.

• 전기전자학회논문지
• /
• 제11권2호
• /
• pp.89-94
• /
• 2007

본 논문은 연속 밀도 함수를 갖는 HMM별 한국어 연속 음성인식에 관한 연구이다. 여기서 우리는 밀도 함수가 2개에서 44개까지 갖는 연속 HMM모델에서 가장 효율적인 연속 음성인식을 위한 방법을 제시한다. 음성 모델은 36개로 구성한 기본음소를 사용한 CI-Model과 3,000개로 구성한 확장음소를 사용한 CD-Model을 사용하였고, 언어 모델은 N-gram을 이용하여 처리하였다. 이 방법을 사용하여 500개의 문장과 6,486개의 단어에 대하여 화자 독립으로 CI Model에서 최고 94.4%의 단어인식률과 64.6%의 문장인식률을 얻었고, CD Model에서는98.2%의 단어인식률과 73.6%의 문장인식률을 안정적으로 얻었다.

• 대한음성학회지:말소리
• /
• 제43호
• /
• pp.89-99
• /
• 2002

Recently, researches into ways of improving large vocabulary continuous speech recognition and speech synthesis are being carried out intensively as the field of speech information technology is progressing rapidly. In the field of speech recognition, developments of stochastic methods such as HMM require large amount of speech data for training, and also in the field of speech synthesis, recent practices show that synthesis of better quality can be produced by selecting and connecting only the variable size of speech data from the large amount of speech data. In this paper we design and discuss linguistic contents for speech copora for speech recognition and synthesis to be shared in common.