• Speech Sciences
• /
• v.12 no.1
• /
• pp.123-134
• /
• 2005

Confidence measure (CM) is used for the rejection of mis-recognized words in an automatic speech recognition (ASR) system. Rahim, Lee, Juang and Cho's confidence measure (RLJC-CM) is one of the widely-used CMs [1]. The RLJC-CM is calculated by averaging phone-level CMs. An extension of the RLJC-CM was achieved by Kim et al [2]. They devised the normalized CM (NCM), which is a statistically normalized version of the RLJC-CM by using the tri-phone based CM normalization. In this paper we verify the NCM by generalizing tri-phone to n-phone unit. To apply various units for the normalization, mono-phone, tri-phone, quin-phone and $\infty$-phone are tested. By the experiments in the domain of the isolated word recognition we show that tri-phone based normalization is sufficient enough to enhance the rejection performance of the ASR system. Also we explain the NCM in regard to two class pattern classification problems.

• Journal of Korea Multimedia Society
• /
• v.17 no.4
• /
• pp.506-513
• /
• 2014

In recent years, research on user's activity recognition using a smart phone has attracted a lot of attentions. A smart phone has various sensors, such as camera, GPS, accelerometer, audio, etc. In addition, smart phones are carried by many people throughout the day. Therefore, we can collect log data from smart phone sensors. The log data can be used to analyze user activities. This paper proposes an approach to inferring a user's physical activities based on the tri-axis accelerometer of smart phone. We propose recognition method for four activity which is physical activity; sitting, standing, walking, running. We have to convert accelerometer raw data so that we can extract features to categorize activities. This paper introduces a recognition method that is able to high detection accuracy for physical activity modes. Using the method, we developed an application system to recognize the user's physical activity mode in real-time. As a result, we obtained accuracy of over 80%.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.75-84
• /
• 2012

HMM-based Text-to-Speech systems generally utilize context dependent tri-phone units from a large corpus speech DB to enhance the synthetic speech. To downsize a large corpus speech DB, acoustically similar tri-phone units are clustered based on the decision tree using context dependent information. Context dependent information includes phoneme sequence as well as prosodic information because the naturalness of synthetic speech highly depends on the prosody such as pause, intonation pattern, and segmental duration. However, if the prosodic information was complicated, many context dependent phonemes would have no examples in the training data, and clustering would provide a smoothed feature which will generate unnatural synthetic speech. In this paper, instead of complicate prosodic information we propose a simple three prosodic boundary types and decision tree questions that use rising tone, falling tone, and monotonic tone to improve naturalness. Experimental results show that our proposed method can improve naturalness of a HMM-based Korean TTS and get high MOS in the perception test.

• PNF and Movement
• /
• v.17 no.2
• /
• pp.167-175
• /
• 2019

Purpose: This study aims to determine the effect of Jeonbuk tri-pull taping and proprioceptive neuromuscular facilitation (PNF) exercise on the shoulder's active range of motion, pain, subluxation, upper extremity function, and activities of daily living in patients with stroke. Methods: In this study, Jeonbuk tri-pull taping and PNF exercise were applied to three patients with stroke and subluxation. The tape was removed and new tape applied for two days every Monday, Wednesday, and Friday over six consecutive weeks. PNF exercise was applied five times a week for six weeks. To measure the range of motion, a smart phone clinometer application was used, and the degree of pain was measured using a visual analogue scale (VAS). A jig measuring method was employed to measure the distance of subluxation. The Fugl-Meyer Assessment (FMA) was used to evaluate arm function, and the modified Barthel Index (MBI) was employed to evaluate the activities of daily living. Results: The shoulder's active range of motion was improved in the patients compared to the range of pre-tests, and the pain and subluxation distance were reduced compared to those of pre-tests. Arm function and activities of daily living were increased compared to those of pre-tests. Conclusion: The study results verified that Jeonbuk tri-pull taping and PNF exercise are useful when applied to patients with subluxation and stroke.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.3
• /
• pp.175-181
• /
• 2003

Because a word of Korean digits is a syllable and deeply coarticulatied in connected digits, some recognition models based on demisyllables have been proposed by researchers. However, they could not show an excellent recognition results yet. This paper proposes a recognition model based on extended and context-dependent demisyllables, such as a tri-demisyllable like a tri-phone, for the Korean 4-connected digits recognition. For experiments, we use a toolkit of HTK 3.0 for building this model of continuous HMMs using training Korean connected digits from SiTEC database and for recognizing unknown ones. The results show that the recognition rate is 92% and this model has an ability to improve the recognition performance of Korean connected digits.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.380-386
• /
• 2002

Conventional post-processing as like confidence measure (CM) proposed by Rahim calculates phones' CM using the likelihood between phoneme model and anti-model, and then word's CM is obtained by averaging phone-level CMs[1]. In conventional method, CMs of some specific keywords are tory low and they are usually rejected. The reason is that statistics of phone-level CMs are not consistent. In other words, phone-level CMs have different probability density functions (pdf) for each phone, especially sri-phone. To overcome this problem, in this paper, we propose normalized confidence measure. Our approach is to transform CM pdf of each tri-phone to the same pdf under the assumption that CM pdfs are Gaussian. For evaluating our method we use common keyword spotting system. In that system context-dependent HMM models are used for modeling keyword utterance and contort-independent HMM models are applied to non-keyword utterance. The experiment results show that the proposed NCM reduced FAR (false alarm rate) from 0.44 to 0.33 FA/KW/HR (false alarm/keyword/hour) when MDR is about 8%. It achieves 25% improvement of FAR.

• Ceramist
• /
• v.22 no.2
• /
• pp.189-197
• /
• 2019

Direct methanol fuel cells (DMFCs) have found a wide variety of commercial applications such as portable computer and mobile phone. In a fuel cell, the catalysts have an important role and durability and efficiency are determined by the ability of the catalyst. The activity of the catalyst is determined by the structure and shape control of the nanoparticles and the dispersion of the nanoparticles and application system. The surface energy of nanoparticles determines the activity by shape control and the nanostructure is determined by the ratio of bi- and tri-metals in the alloy and core-shell. The dispersion of nanoparticles depends on the type of support such as carbon, graphen and metal oxide. In addition, a hybrid system using both optical and electrochemical device has been developed recently.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.12
• /
• pp.125-132
• /
• 2010

In vocabulary recognition has unseen tri-phone appeared when recognition training. This system has not been created beginning estimation figure of model parameter. It's bad points could not be created that model for phoneme data. Therefore it's could not be secured accuracy of Gaussian model. To improve suggested Gaussian model to optimized method of model parameter using probability distribution. To improved of confidence that Gaussian model to optimized of probability distribution to offer by accuracy and to support searching of phoneme data. This paper suggested system performance comparison as a result of recognition improve represent 1.7% by out-of vocabulary rejection algorithm using normalization confidence.

• Journal of the Korean Society of Physical Medicine
• /
• v.13 no.3
• /
• pp.19-25
• /
• 2018

PURPOSE: Most gait assessment tools are expensive and require controlled laboratory environments. Tri-axial accelerometers have been used in gait analysis as an alternative to laboratory assessments. Many smartphones have added an accelerometer, making it possible to assess spatio-temporal gait parameters. This study was conducted to confirm the reliability and validity of a smartphone-based accelerometer at quantifying spatio-temporal gait parameters of stroke patients when attached to the body. METHODS: We measured gait parameters using a smartphone accelerometer and gait parameters through the GAITRite analysis system and the reliability and validity of the smartphone-based accelerometer for quantifying spatio-temporal gait parameters for stroke patients were then evaluated. Thirty stroke patients were asked to walk at self-selected comfortable speeds over a 10 m walkway, during which time gait velocity, cadence and step length were computed from smartphone-based accelerometers and validated with a GAITRite analysis system. RESULTS: Smartphone data was found to have excellent reliability ($ICC2,1{\geq}.98$) for measuring the tested parameters, with a high correlation being observed between smartphone-based gait parameters and GAITRite analysis system-based gait parameters (r = .99, .97, .41 for gait velocity, cadence, step length, respectively). CONCLUSION: The results suggest that specific opportunities exist for smartphone-based gait assessment as an alternative to conventional gait assessment. Moreover, smartphone-based gait assessment can provide objective information about changes in the spatio-temporal gait parameters of stroke subjects.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.2
• /
• pp.168-180
• /
• 1992

Commumication technology has been continuously developed to overcome the distance and time for the transmission of information to the human society. Wireless mobile communication, which had been used mostly in the military and police is widely used these days for enterprise and individuals. Therefore the domestic usage of the advanced mobile phone service are progressively gaining wide popularity. The modulation techniques used usually in mobile communications were the analog techniques such as AM and FM, but they are getting replaced by the digital techniques, However, the major disadvantage of the digital communications is the increase of the transmission bandwidth. Therefore, it is very important to use efficiently the limited frequency bandwidth. The domestic research and development on the subject seems quite limited and in order to establish the technology of the digital mobile communications. This thesis presents the design of the frequency hopping synthesizer providing 124 channels with a channel spcing of 200KHz. VCD used in the synthesizer employs a semi-rigid cable for higher purity of signal spectrum, and a hybrid pgase detector is realized with a sample hold phase detector in conjuction with a tri-state phase detedctor.