• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.321-322
• /
• 2007

When use FMO by error resilience purpose in existing $TYPE1{\sim}2$ compare. But, in This paper, TYPE $3{\sim}5$[Gradual decoder refresh tool] is used as error resilence tool. Experiment result, it shows that Y PSNR improves that use suitable TYPE's FMO. Images using in an experiment had better use Type $3{\sim}5$. Differ with existing paper, dipersed mode appeared result badly. Because spatial correlation is low, acted adversely in intra predication.

• Science of Emotion and Sensibility
• /
• v.21 no.1
• /
• pp.59-70
• /
• 2018

With the breakthrough of speech recognition technology, conversational agents have become pervasive through smartphones and smart speakers. The recognition accuracy of speech recognition technology has developed to the level of human beings, but it still shows limitations on understanding the underlying meaning or intention of words, or understanding long conversation. Accordingly, the users experience various errors when interacting with the conversational agents, which may negatively affect the user experience. In addition, in the case of smart speakers with a voice as the main interface, the lack of feedback on system and transparency was reported as the main issue when the users using. Therefore, there is a strong need for research on how users can better understand the capability of the conversational agents and mitigate negative emotions in error situations. In this study, we applied social strategies, "forewarning" and "apology", to conversational agent and investigated how these strategies affect users' perceptions of the agent in breakdown situations. For the study, we created a series of demo videos of a user interacting with a conversational agent. After watching the demo videos, the participants were asked to evaluate how they liked and trusted the agent through an online survey. A total of 104 respondents were analyzed and found to be contrary to our expectation based on the literature study. The result showed that forewarning gave a negative impression to the user, especially the reliability of the agent. Also, apology in a breakdown situation did not affect the users' perceptions. In the following in-depth interviews, participants explained that they perceived the smart speaker as a machine rather than a human-like object, and for this reason, the social strategies did not work. These results show that the social strategies should be applied according to the perceptions that user has toward agents.

• Phonetics and Speech Sciences
• /
• v.4 no.1
• /
• pp.29-47
• /
• 2012

The purpose of this paper is to show how to convert the label files of the Buckeye Corpus of Spontaneous Speech [1] into Praat format and to introduce some of the Praat scripts that will enable linguists to study various aspects of spoken American English present in the corpus. During the conversion process, several types of errors were identified and corrected either manually or automatically by the use of scripts. The Praat script tools that have been developed can help extract from the corpus massive amounts of phonetic measures such as the VOT of plosives, the formants of vowels, word frequency information and speech rates that span several consecutive words. The script tools can extract additional information concerning the phonetic environment of the target words or allophones.

• ETRI Journal
• /
• v.41 no.1
• /
• pp.109-116
• /
• 2019

This paper explores new techniques that are based on a hidden-layer linear transformation for fast speaker adaptation used in deep neural networks (DNNs). Conventional methods using affine transformations are ineffective because they require a relatively large number of parameters to perform. Meanwhile, methods that employ singular-value decomposition (SVD) are utilized because they are effective at reducing adaptive parameters. However, a matrix decomposition is computationally expensive when using online services. We propose the use of an extended diagonal linear transformation method to minimize adaptation parameters without SVD to increase the performance level for tasks that require smaller degrees of adaptation. In Korean large vocabulary continuous speech recognition (LVCSR) tasks, the proposed method shows significant improvements with error-reduction rates of 8.4% and 17.1% in five and 50 conversational sentence adaptations, respectively. Compared with the adaptation methods using SVD, there is an increased recognition performance with fewer parameters.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.553-558
• /
• 2022

최근, 구어체 데이터에 대한 자연어처리 응용 기술이 늘어나고 있다. 구어체 문장은 소통 방식 등의 형태로 인해 정제되지 않은 형태로써, 필연적으로 띄어쓰기, 문장 왜곡 등의 다양한 문법적 오류를 포함한다. 자동 문법 교정기는 이러한 구어체 데이터의 전처리 및 일차적 정제 도구로써 활용된다. 사전학습된 트랜스포머 기반 문장 생성 연구가 활발해지며, 이를 활용한 자동 문법 교정기 역시 연구되고 있다. 트랜스포머 기반 문장 교정 시, 교정의 필요 유무를 잘못 판단하여, 오류가 생기게 된다. 이러한 오류는 대체로 문맥에 혼동을 주는 단어의 등장으로 인해 발생한다. 본 논문은 트랜스포머 기반 문법 교정기의 오류를 보강하기 위한 방식으로써, 필요하지 않은 형태소인 고유명사를 마스킹한 입력 및 출력 문장틀 형태를 제안하며, 이러한 문장틀에 대해 고유명사를 복원한 경우 성능이 증강됨을 보인다.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2
• /
• pp.88-95
• /
• 2006

In this Paper. a method for improving the performance of automatic speech recognition (ASR) system for conversational speech is proposed. which mainly focuses on increasing the robustness against the rapidly speaking utterances. The proposed method doesn't require an additional speech recognition task to represent speaking rate quantitatively. Energy distribution for special bands is employed to detect the vowel regions, the number of vowels Per unit second is then computed as speaking rate. To improve the Performance for fast speech. in the pervious methods. a sequence of the feature vectors is expanded by a given scaling factor, which is computed by a ratio between the standard phoneme duration and the measured one. However, in the method proposed herein. utterances are classified by their speaking rates. and the scaling factor is determined individually for each class. In this procedure, a maximum likelihood criterion is employed. By the results from the ASR experiments devised for the 10-digits mobile phone number. it is confirmed that the overall error rate was reduced by $17.8\%$ when the proposed method is employed

• Education of Primary School Mathematics
• /
• v.27 no.3
• /
• pp.303-320
• /
• 2024

This study presents the development and performance evaluation of a custom GPT-based chatbot tailored to provide solutions following Polya's problem-solving stages. A beta version of the chatbot was initially deployed to assess its mathematical capabilities, followed by iterative error identification and correction, leading to the final version. The completed chatbot demonstrated an accuracy rate of approximately 89.0%, correctly solving an average of 57.8 out of 65 image-based problems from a 6th-grade elementary mathematics textbook, reflecting a 4 percentage point improvement over the beta version. For a subset of 50 problems, where images were not critical for problem resolution, the chatbot achieved an accuracy rate of approximately 91.0%, solving an average of 45.5 problems correctly. Predominant errors included problem recognition issues, particularly with complex or poorly recognizable images, along with concept confusion and comprehension errors. The custom chatbot exhibited superior mathematical performance compared to the general-purpose ChatGPT. Additionally, its solution process can be adapted to various grade levels, facilitating personalized student instruction. The ease of chatbot creation and customization underscores its potential for diverse applications in mathematics education, such as individualized teacher support and personalized student guidance.