• Phonetics and Speech Sciences
• /
• v.11 no.3
• /
• pp.39-47
• /
• 2019

We propose a method to improve the performance of spontaneous speech recognizers by extending their phone set using speech data. In the proposed method, we first extract variable-length phoneme-level segments from broadcast speech signals, and convert them to fixed-length latent vectors using an long short-term memory (LSTM) classifier. We then cluster acoustically similar latent vectors and build a new phone set by choosing the number of clusters with the lowest Davies-Bouldin index. We also update the lexicon of the speech recognizer by choosing the pronunciation sequence of each word with the highest conditional probability. In order to analyze the acoustic characteristics of the new phone set, we visualize its spectral patterns and segment duration. Through speech recognition experiments using a larger training data set than our own previous work, we confirm that the new phone set yields better performance than the conventional phoneme-based and grapheme-based units in both spontaneous speech recognition and read speech recognition.

• Journal of the Korean Society for Precision Engineering
• /
• v.27 no.11
• /
• pp.63-71
• /
• 2010

FormFactors is one of the most critical design factors in early development of mobile phone, and proper selection of FormFactors is necessary for smoothness of product development and customer satisfaction. Especially, emergence of mobile convergence added so various functions besides its original call function that importance of selecting FormFactors has increased because multiform FormFactors are needed. However there is problem such as frequent change of decision making in existing process because established process picks out FormFactors sensibly and arbitrarily through idea pull and so forth. We proposed FormFactors selection process by Axiomatic Design, set approach method and block approach method for reasonable and systematical FormFactors selection. First of all, we set the purpose of mobile phone development, and it is examined by Axiomatic Design. FormFactors design matrix is deduced through this process, the numbers of axes and rails are proposed using set approach method, and then patterns of FormFactors are embodied by block approach method. Particularly process application was tried through case study of mobile phone development, and we ensured that new FormFactors can be presented to a designer by systematical verification if change of customer requirements occurs through our process.

• MALSORI
• /
• no.62
• /
• pp.133-147
• /
• 2007

In this paper, we introduce a phone vector discrete HMM(PVDHMM) that decodes a phone sequence string, and demonstrates the applicability to spoken document retrieval. The PVDHMM treats a phone recognizer or large vocabulary continuous speech recognizer (LVCSR) as a vector quantizer whose codebook size is equal to the size of its phone set. We apply the PVDHMM to decode the phone sequence strings and compare the outputs with those of a continuous speech recognizer(CSR). Also we carry out spoken document retrieval experiment through PVDHMM word spotter on the phone sequence strings which are generated by phone recognizer or LVCSR and compare its results with those of retrieval through the phone-based vector space model.

• MALSORI
• /
• no.65
• /
• pp.105-124
• /
• 2008

This paper presents the effects of different phone-like-unit (PLU) sets in order to propose an optimal PLU set for the performance improvement of Korean automatic speech recognition (ASR) systems. The examination of 9 currently used PLU sets indicates that most of them include a selection of allophones without any sufficient phonetic base. In this paper, a total of 34 PLU sets are designed based on Korean phonetic characteristics arid the effects of each PLU set are evaluated through experiments. The results show that the accuracy rate of each phone is influenced by different phonetic constraint(s) which determine(s) the PLU sets, and that an optimal PLU set can be anticipated through the phonetic analysis of the given speech data.

• Journal of the Ergonomics Society of Korea
• /
• v.26 no.3
• /
• pp.53-57
• /
• 2007

The User Interface (UI) in the company is more important than ever. But the application of UI for the industry use is restricted by various constraints such as delivery, technical limitation, etc. User Interface designers in the company have thought how to set up the UI organization, how to define identity and goal, how to communicate with other teams, what is the best UI process, and many other issues. In this paper, the author discuss the practical issues arisen when User Interface organization is formed and managed based on the mobile phone manufacture's perspective. The pros and cons of location of UI organization, advanced UI organization, UI member formation, UI role, UI output, UI evaluation, and understanding of UI in the society and company are discussed. This discussion will help UI designers in industry to set up and manage UI organization.

• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.4
• /
• pp.431-438
• /
• 2000

The purpose of this paper is to design the menu of mobile phone based on the impression engineering. Free response survey analysis was used to collect impression data on mobile phone functions with time interval. Simultaneity analysis was applied to finding the relationship among selected impression. We cluster a set of the related impression so as to design the menu of a mobile phone accordingly. This research is expected to contribute to the improvement of customer satisfaction by reflecting customer's impression in the process of product design.

• The Journal of Society for e-Business Studies
• /
• v.20 no.1
• /
• pp.99-115
• /
• 2015

This study aims to classify the pursuit benefits of smart-phone users, to find smart-phone market segments by pursuit benefits, and to analyze the relative importances of smart-phone attributes according to the smart-phone market segments. As a result, we found that smart-phone users are pursuing the network benefit as well as the two traditional benefits (the utilitarian benefit and the hedonic benefit). According to the levels of these three pursuit benefits, smart-phone users can be classified into four segments : All Benefits Cluster, Utilitarian-Network Benefits Cluster, Hedonic-Network Benefits Cluster, and Non-Network Benefits Cluster. We also verified that, according to the four smart-phone user segments by the pursuit benefits, there exist significant differences in relative importances of the seven smart-phone attributes : hand-set price, hand-set brand, hand-set speed, applications, tariff, mobile internet quality, and number of same service users.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.05a
• /
• pp.356-361
• /
• 2001

A research to maximize the force transmitted from a vibration motor at the vibration mode, installed in the cellular phone jig, is presented in this study. When the natural frequencies corresponding to the structural vibration modes of the set exist within the range of the driving frequencies acquired by changing the RPM of the vibration motor, the structural vibration resonance is applicable to maximization of the vibration force sensible to the human body such as hands, arms, and hips. The analytical modal analysis using the Finite Elements and the experimental modal testing for the set jig were performed in order to understand the structural modes and the corresponding frequencies. Then the dynamic responses of the set jig to the given driving frequency were measured and the results on maximizing the vibration were confirmed by the FEM dynamic simulation.

• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.5 s.182
• /
• pp.119-127
• /
• 2006

Design structure of a mobile phone has been changed to a converged style, which has so many functions. However, the converged mobile phone could not satisfy the users who want to use only specific functions, so with Axiomatic Design, we have studied for making a proposal to set up the new concept. The goal of this study is to derive a general solution with Axiomatic Design to verify the Independence. By enhancing the existing design model and differentiating the function of mobile phone, user will be able to choose desirable products, which have only specific functions and/or specific parts. First of all, we checked the Independence about the existing design model. Then, we developed the new design model with the idea that base mobile phone should have basic functions and additional functions can be separated, surely be connected when users want.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.105-108
• /
• 2000

CTI[1]의 응용 영역 중에서 인터넷 폰이 최근 뜨거운 관심의 대상으로 떠오르고 있다. 인터넷을 이용한 음성전달 기술은 인터넷의 성장 보급과 더불어 나날이발전 하고 있는데, 이러한 음성전달기술을 이용해 개발된 소프트 웨어를 통칭해서 인터넷 폰이라고 부르고 있다. 이러한 변화 속에서 비용의 절감과 비디오 전화, 영상회의와 같은 응용에 적용할 수 있는, 본 개발은 One Encoder One Decoder 지원의 VoIP(Voice over Internet Protocol) Phone에 관한 것으로, 특히 압축하여 인터넷 망에 접속시켜 사용할 수 있는 PC 장착형 One Board 형태의 시스템을 구현하였다. 이 Board에 사용 된 칩셋은 국내 회사인 C&S Technology 사의SEAGUL723이며, PC인터페이스는 PCI(Peripheral Component Interconnect) 버스 방식을 이용하였다. 주요 연구내용에 있어서 하드웨어 부분은 내선제어모듈,PCI 모듈, 칩셋을 이용한 음성신호처리 모듈, Board제어 모듈 등이 있으며, 소프트 웨어 설계 부분에 있어서는 하드웨어 구동을 위한 시스템 드라이브, Application과 인터넷 상의 VoIP 통신을 위한 소프트웨어, 사용자를 위한 User Interface 소프트 웨어 등이 있다.