• Journal of Korea Game Society
• /
• v.12 no.1
• /
• pp.123-132
• /
• 2012

There are many of games using smart devices. Voice recognition is can be useful way for input. In the game, voice have to be quickly recognized, at the same time it have to be manipulated promptly as well. In this study, we developed the optimized real-time phoneme recognition using max flow matching that it can be efficiently used in the game field. Firstly, voice wavelength is transformed to FFT, secondly, transformed value is made by a graph in Z plane, thirdly, data is extracted in specific area, and then data is saved in database. After all the value is recognized using weighted bipartite max flow matching. This way would be useful method in game or robot field when researchers hope to recognize the fast voice recognition.

• Journal of Digital Contents Society
• /
• v.16 no.2
• /
• pp.219-225
• /
• 2015

This experimental study aims at understanding the Korean subjects' phonemic awareness in the English minimal pairs. For the purpose of the experiment, English listening comprehension tests were designed using minimal pairs and conducted among subjects, and the results of the tests were analyzed with the help of spectrogram. From the results of this study, I could find out three important things: First, subjects have difficulty in understanding and distinguishing English vowel minimal pairs. Second, among the English vowel minimal pairs, they had much difficulty in distinguishing between /ə:/ and /ɔ:/. Third, subjects could recognize the semivowel /w/ in words without any difficulty. In addition to this, I tried to analyze the results using the spectrogram, which helps to educate students effectively.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.84-88
• /
• 1999

The accurate estimation of segmental duration is crucial for natural-sounding text-to-speech synthesis. For predicting Korean segmental durations, conventional methods utilized phonemic context, part-of-speech context and locational information in prosodic phrase. In this paper, the tonal information of phonemes is employed for more accurate prediction. After defining two non-boundary tones and six boundary tones, we annotated the tonal label on each syllable of 400 sentences. To predict segmental duration using tonal information, we constructed neural networks with a real-valued output node predicting phonemic duration and trained them by backpropagation algorithm. Experimental results showed that the proposed features are effective for predicting Korean segmental durations, and we got 0.863 correlation coefficient of the observed durations and predicted ones.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1995.06a
• /
• pp.73-75
• /
• 1995

연속 음성 인식을 위한 신경망과 학습속도를 줄이기 위한 연결강도 초기화에 관해 다루고 있다. 우선 음소를 여러개의 그룹으로 나눈 후 각각의그룹에 대한 음소를 인식하는 신경망과 자신의 그룹을 판별하는 VGNN 으로 신경망을 구성한다. 여기서 구성되는 신경망은 각각의 음소를 인식하는 출력을 낼 뿐 아니라, 입력이 자신의 그룹에 속하는지 그렇지 않은지를 판별하는 출력을 낸다. 이런 신경망을 학습시키는 데 상당한 시간이 걸리므로 이 신경망의 학습속도를 줄이기 위해 학습 데이터를 사용하여 신경망의 연결 강도를 초기화한다.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.455-461
• /
• 2002

This paper presents a method that improves the performance of the personal voice dialling system in which speaker independent phoneme HMM's are used. Since the speaker independent phoneme HMM based voice dialing system uses only the phone transcription of the input sentence, the storage space could be reduced greatly. However, the performance of the system is worse than that of the system which uses the speaker dependent models due to the phone recognition errors generated when the speaker independent models are used. In order to solve this problem, a new method that jointly estimates transformation vectors for the speaker adaptation and transcriptions from training utterances is presented. The biases and transcriptions are estimated iteratively from the training data of each user with maximum likelihood approach to the stochastic matching using speaker-independent phone models. Experimental result shows that the proposed method is superior to the conventional method which used transcriptions only.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.1
• /
• pp.4-10
• /
• 2000

The work presented in this paper is about a postprocessor, which improves the performance of automatic speech segmentation system by correcting the phoneme boundary errors. We propose a postprocessor that reduces the range of errors in the auto labeled results that are ready to be used directly as synthesis unit. Starting from a baseline automatic segmentation system, our proposed postprocessor trains the features of hand labeled results using multi-layer perceptron(MLP) algorithm. Then, the auto labeled result combined with MLP postprocessor determines the new phoneme boundary. The details are as following. First, we select the feature sets of speech, based on the acoustic phonetic knowledge. And then we have adopted the MLP as pattern classifier because of its excellent nonlinear discrimination capability. Moreover, it is easy for MLP to reflect fully the various types of acoustic features appearing at the phoneme boundaries within a short time. At the last procedure, an appropriate feature set analyzed about each phonetic event is applied to our proposed postprocessor to compensate the phoneme boundary error. For phonetically rich sentences data, we have achieved 19.9 % improvement for the frame accuracy, comparing with the performance of plain automatic labeling system. Also, we could reduce the absolute error rate about 28.6%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.1026-1029
• /
• 2019

최근 제안되고 있는 Bert 등의 딥러닝 언어 모델 기반 pre-training 기법은 다양한 NLP 분야에서 활용되고 있다. 텍스트로 작성된 데이터 셋을 딥러닝 언어 모델이 학습하기 위해서는 토크나이징(tokenizing) 기술이 필요하다. 그러나 기존 토크나이징 방식은 한국어 및 한글이 가지는 고유한 특성(교착어적 특성과 모아쓰기 반영)을 반영하기 어렵다는 한계를 가지고 있다. 본 논문에서는 한국어와 한글이 가지는 고유한 특성을 고려하기 위하여 음소 단위의 임베딩 기법을 제안하며, 이를 기반으로 언어 모델을 설계 및 구현한다. 또한 음소 단위 임베딩 기반 한국어 모델이 실제 데이터 집합(구약성서)에서 나타나는 언어적 패턴을 학습할 수 있다는 것을 실험을 통하여 밝힌다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.767-770
• /
• 2005

네트워크상에서 전달되는 음성데이터는 전달되는 과정에서 잡음 등의 외부 요인으로 인하여 데이터에 손실이 생기는 문제가 발생한다. 이렇게 전달된 음성데이터가 음성 인식기를 통과하면 바로 음성 인식기를 통과했을 때 보다 인식률이 낮아진다. 본 연구에서는 홈 네트워크를 제어하는데 있어서 음성 인식률을 향상시키기 위해서 음성 데이터를 입력받아, 이를 음소단위 기반의 유사율 알고리즘을 적용시켜 이미 구축된 홈 네트워크 용어 관련 사전에 등록된 단어와의 유사성을 검토하여 추출된 결과로 홈 네트워크를 제어하는 방안을 제안한다. 음소단위 기반의 유사율 알고리즘과 다중발화를 이용했을 때 Threshold 값이 85% 일 경우 사전에 구축된 단어와 매칭된 인식률은 100%였으며, 사전에 없는 단어의 오인식률은 2%로 감소되었다.

• Journal of Korea Multimedia Society
• /
• v.14 no.1
• /
• pp.85-93
• /
• 2011

Previous existing vocabulary recognition programs calculate general vector values from a database, so they can not process phonemes that form during a search. And because they can not create a model for phoneme data, the accuracy of the Gaussian model can not secure. Therefore, in this paper, we recommend use of the Bhattacharyya distance measurement method based on the features of the phoneme-thus allowing us to improve the recognition rate by picking up accurate phonemes and minimizing recognition of similar and erroneous phonemes. We test the Gaussian model optimization through share continuous probability distribution, and we confirm the heighten recognition rate. The Bhattacharyya distance measurement method suggest in this paper reflect an average 1.9% improvement in performance compare to previous methods, and it has average 2.9% improvement based on reliability in recognition rate.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.772-774
• /
• 2004

음성인식 시스템에서 입력된 음성 데이터에 대해 비인식 대상에 대한 거부기능은 신뢰도 보장 측면에서 상당히 중요하다. 비인식 대상의 단어 거부는 지금까지 여러 연구가 이루어져 왔으나, 문장 거부에 대한 연구는 사실상 부족한 실정이다. 본 논문에서는 비인식 대상 문장 거부기능의 신뢰도를 한층 높일 수 있도록 음소 기반 네트워크에 유성자음(VC), 무성자음(C), 모음(V) 단위의 필러 음향 모델을 생성하여 다양한 음소기반 인식 네트워크의 구성방법을 적용하여 비인식 대상 문장에 대해 거부 기능을 구현하고, 그에 따라 인식률과 거부율이 달라질 수 있음을 보인다. 구현된 시스템에서 제안한 3가지 음소단위 인식 네트워크 중 문장의 각 단어별 필러 모델을 구성했을 때가 가장 좋은 구성임을 알 수 있었다.