• 음성과학
• /
• 제13권4호
• /
• pp.177-186
• /
• 2006

In an effort to enhance the quality of feature vector classification and thereby reduce the recognition error rate of the speaker-independent speech recognition, we employ the Mahalanobis distance in the calculation of the similarity measure between feature vectors. It is assumed that the metric matrix of the Mahalanobis distance be diagonal for the sake of cost reduction in memory and time of calculation. We propose that the diagonal elements be given in terms of the variations of the feature vector components. Geometrically, this prescription tends to redistribute the set of data in the shape of a hypersphere in the feature vector space. The idea is applied to the speech recognition by hidden Markov model with fuzzy vector quantization. The result shows that the recognition is improved by an appropriate choice of the relevant adjustable parameter. The Viterbi score difference of the two winners in the recognition test shows that the general behavior is in accord with that of the recognition error rate.

• 음성과학
• /
• 제8권3호
• /
• pp.123-132
• /
• 2001

In recent years research on HCI technology has been very active and speech recognition is being used as its typical method. Its recognition, however, is deteriorated with the increase of surrounding noise. To solve this problem, studies concerning the multimodal HCI are being briskly made. This paper describes automated lipreading for bimodal speech recognition on the basis of image- and speech information. It employs audio-visual DB containing 1,074 words from 70 voice and tri-viseme as a recognition unit, and state tied HMM as a recognition model. Performance of automated recognition of 22 to 1,000 words are evaluated to achieve word recognition of 60.5% in terms of 22word recognizer.

• 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.

• 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.

• 음성과학
• /
• 제4권2호
• /
• pp.25-39
• /
• 1998

This paper deals with fuzzy correlation dimension for an appropriate speech recognition. The proposed fuzzy correlation dimension has absorbed time variation value of strange attractor as utilizing fuzzy membership function at calculation of integral correlation when the results of proposed dimension are applied to speech recognition fuzzed correlation dimension is superior to speech recognition, and correlation dimension is superior to speaker discrimination.

• 전자공학회논문지S
• /
• 제34S권5호
• /
• pp.86-93
• /
• 1997

With recent development of speech recognition technology and multimedia computer systems, more potential applications of voice will become a reality. In this paper, we implement speech interface on the windows95 environment for practical use fo multimedia computers with voice. Speech interface is made up of three modules, that is, speech input and detection module, speech recognition module, and application module. The speech input and etection module handles th elow-level audio service of win32 API to input speech data on real time. The recognition module processes the incoming speech data, and then recognizes the spoken command. DTW pattern matching method is used for speech recognition. The application module executes the voice command properly on PC. Each module of the speech interface is designed and examined on windows95 environments. Implemented speech interface and experimental results are explained and discussed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.685-688
• /
• 2000

In this paper, we used image information for the enhancement of Korean numeral speech recognition. First, a noisy environment was made by Gaussian generator at each 10 dB level and the generated signal was added to original Korean numeral speech. And then, the speech was analyzed to recognize Korean numeral speech. Speech through microphone was pre-emphasized with 0.95, Hamming window, autocorrelation and LPC analysis was used. Second, the image obtained by camera, was converted to gray level, autocorrelated, and analyzed using LPC algorithm, to which was applied in speech analysis, Finally, the Korean numerial speech recognition with image information was more ehnanced than speech-only, especially in ‘3’, ‘5’and ‘9’. As the same LPC algorithm and simple image management was used, additional computation a1gorithm like a filtering was not used, a total speech recognition algorithm was made simple.

• 말소리와 음성과학
• /
• 제2권3호
• /
• pp.141-148
• /
• 2010

In this paper, voice activity detection (VAD) for dual-channel noisy speech recognition is proposed in which spatial cues are employed. In the proposed method, a probability model for speech presence/absence is constructed using spatial cues obtained from dual-channel input signal, and a speech activity interval is detected through this probability model. In particular, spatial cues are composed of interaural time differences and interaural level differences of dual-channel speech signals, and the probability model for speech presence/absence is based on a Gaussian kernel density. In order to evaluate the performance of the proposed VAD method, speech recognition is performed for speech segments that only include speech intervals detected by the proposed VAD method. The performance of the proposed method is compared with those of several methods such as an SNR-based method, a direction of arrival (DOA) based method, and a phase vector based method. It is shown from the speech recognition experiments that the proposed method outperforms conventional methods by providing relative word error rates reductions of 11.68%, 41.92%, and 10.15% compared with SNR-based, DOA-based, and phase vector based method, respectively.

• 한국정보통신학회논문지
• /
• 제18권10호
• /
• pp.2367-2374
• /
• 2014

본 논문에서는 이기종 음성 인식 시스템에 독립적으로 적용할 수 있는 음성 향상 기법을 제안한다. 잡음 환경 음성 인식에 효과적인 것으로 알려져 있는 특징 보상 기법이 효과적으로 적용되기 위해서는 특징 추출 기법와 음향 모델이 음성 인식 시스템과 일치해야 한다. 상용화된 음성 인식 시스템에 부가적으로 전처리 기법을 적용하는 상황과 같이, 음성 인식 시스템에 대한 정보가 알려져 있지 않은 상황에서는 기존의 특징 보상 기법을 적용하기가 어렵다. 본 논문에서는 기존의 PCGMM 기반의 특징 보상 기법에서 얻어지는 이득을 이용하는 음성 향상 기술을 제안한다. 실험 결과에서는 본 논문에서 제안하는 기법이 미지의 (Unknown) 음성 인식 시스템 적용 환경에서 기존의 전처리 기법에 비해 다양한 잡음 및 SNR 조건에서 월등한 인식 성능을 나타내는 것을 확인한다.

• 한국음향학회지
• /
• 제40권5호
• /
• pp.515-522
• /
• 2021

음성감정인식을 위한 훈련 데이터는 감정 레이블링의 어려움으로 인해 충분히 확보하기 어렵다. 본 논문에서는 음성감정인식의 성능 개선을 위해 트랜스포머 기반 모델에 대규모 음성인식용 훈련 데이터를 통한 전이학습을 적용한다. 또한 음성인식과의 다중작업학습을 통해 별도의 디코딩 없이 문맥 정보를 활용하는 방법을 제안한다. IEMOCAP 데이터 셋을 이용한 음성감정인식 실험을 통해, 가중정확도 70.6 % 및 비가중정확도 71.6 %를 달성하여, 제안된 방법이 음성감정인식 성능 향상에 효과가 있음을 보여준다.