• Speech Sciences
• /
• v.1
• /
• pp.137-152
• /
• 1997

The objectives of this paper are to see how the declination is realized in the different positions/lengths of the utterance, to see if the $F_0$ value throughout the utterance changes in a predictable way, and if so, to find out the best quantitative model which fits the declination. The experiment results are as follows. First, the peak value over the utterance can be affected by the position of the peak and length of the utterance. Second, the choice of quantitative models is dependent on the different list lengths. Third, in everyone's speech, there is a baseline (the lowest $F_0$ value a speaker can use), and the $F_0$ will not fall below the baseline. Forth, the peak $F_0$ of the last word in each list shows little variation in pitch value (target $F_0$) while the number of words in the list affects the starting $F_0$ values.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.479-481
• /
• 2019

본 연구에서는 이미지를 분류하는 인공 신경망 가속기를 최적화했고, 이를 구현하여 기존 인공 신경망 가속기와 성능을 비교 분석했다. FPGA(Field Programmable Fate Array) 보드를 이용하여 가속기를 구현했으며, 해당 보드의 내부 메모리인 BRAM 을 FIFO(First In First Out)구조로 설계하여 메모리 시스템을 구현했다. Approximate computing 기법을 효율적으로 적용하기 위해 FWL(Fractional Word Length)최적점을 분석했고, 이를 기반으로 인공 신경망 가속기의 부동 소수점 연산을 고정 소수점 연산으로 변환했다. 구현된 인공 신경망 가속기는 기존의 인공 신경망에 비해, 약 7.4%더 효율적인 전력소모량을 보였다.

• Proceedings of the KSPS conference
• /
• 1996.10a
• /
• pp.37-42
• /
• 1996

This study aims to see some prosodic features of English spoken by Japanese learners of English. It focuses on speech rates, pauses, and intonation when the learners read an English passage. Three Japanese learners of English, who are all male university students, were asked to read the speech material, an English passage of 110 word length, at their normal reading speed. Then a native speaker of English, a male American English teacher. was asked to read the same passage. The Japanese speakers were also asked to read a Japanese passage of 286 letters (Japanese Kana) to compare the reading of English with that of japanese. Their speech was analyzed on a computerized system (KAY Computerized Speech Lab). Wave forms, spectrograms, and F0 contours were shown on the screen to measure the duration of pauses, phrases and sentences and to observe intonation contours. One finding of the experiment was that the movement of the low speakers' speech rates showed a similar tendency in their reading of the English passage. Reading of the Japanese passage by the three learners also had a similar tendency in the movement of speech rates. Another finding was that the frequency of pauses in the learners speech was greater than that in the speech of the native speaker, but that the ration of the total pause length to the whole utterance length was about tile same in both the learners' and the native speaker's speech. A similar tendency was observed about the learners' reading of the Japanese passage except that they used shorter pauses in the mid-sentence position. As to intonation contours, we found that the learners used a narrower pitch range than the native speaker in their reading of the English passage while they used a wider pitch range as they read the Japanese passage. It was found that the learners tended to use falling intonation before pauses whereas the native speaker used different intonation patterns. These findings are applicable to the teaching of English pronunciation at the passage level in the sense that they can show the learners. Japanese here, what their problems are and how they could be solved.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.3
• /
• pp.111-116
• /
• 2013

With technology scaling, soft error rate has greatly increased in embedded systems. Due to high performance and low power consumption, VLIW (Very Long Instruction Word) architectures have been widely used in embedded systems and thus many researches have been studied to improve the reliability of a system by duplicating instructions in VLIW architectures. However, existing studies have ignored the feature, called VLES (Variable Length Execution Set), which is adopted in most modern VLIW architectures to reduce code size. In this paper, we propose how to support instruction duplication in VLIW architecture with VLES. Our experimental results demonstrate that a VLIW architecture with VLES shows 64% code size decrement on average at the cost of about 4% additional cell area as compared to the case of a VLIW architecture without VLES when instruction duplication is applied to both architectures. Also, it is shown that the case with VLES does not cause extra execution time compared to the case without VLES.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.681-686
• /
• 2012

This paper studied the speech parameters less affected by the human emotion for the development of the robust emotional speech recognition system. For this purpose, the effect of emotion on the speech recognition system and robust speech parameters of speech recognition system were studied using speech database containing various emotions. In this study, mel-cepstral coefficient, delta-cepstral coefficient, RASTA mel-cepstral coefficient, root-cepstral coefficient, PLP coefficient and frequency warped mel-cepstral coefficient in the vocal tract length normalization method were used as feature parameters. And CMS (Cepstral Mean Subtraction) and SBR(Signal Bias Removal) method were used as a signal bias removal technique. Experimental results showed that the HMM based speaker independent word recognizer using frequency warped RASTA mel-cepstral coefficient in the vocal tract length normalized method, its derivatives and CMS as a signal bias removal showed the best performance.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.5
• /
• pp.567-575
• /
• 2001

This paper suggests new method to get fixed size parameter from different length of voice signals. The efficiency of speech recognizer is determined by how to compare the similarity(distance of each pattern) of the parameter from voice signal. But the variation of voice signal and the difference of speech speed make it difficult to extract the fixed size parameter from the voice signal. The method suggested in this paper is to normalize the parameter at fixed size by using the 2 dimension DCT(Discrete Cosine Transform) after representing the parameter by spectrogram. To prove validity of the suggested method, parameter extracted from 32 auditory filter-bank(it estimates auditory nerve firing probabilities) is used for the input of neural network after being processed by 2 dimension DCT. And to compare with conventional methods, we used one of conventional methods which solve time alignment problem. The result shows more efficient performance and faster recognition speed in the speaker dependent and independent isolated word recognition than conventional method.

• Journal of KIISE:Software and Applications
• /
• v.34 no.2
• /
• pp.140-149
• /
• 2007

This paper presents a statistical model for Korean dependency-based parsing. Although Korean is one of free word order languages, it has the feature of which some word order is preferred to local contexts. Earlier works proposed parsing models using modification lengths due to this property. Our model uses headible path contexts for modification length probabilities. Using a headible path of a dependent it is effective for long distance relation because the large surface context for a dependent are abbreviated as its headible path. By combined with lexical bigram dependency, our probabilistic model achieves 86.9% accuracy in eojoel analysis for KAIST corpus, more improvement especially for long distance dependencies.

• Fashion & Textile Research Journal
• /
• v.16 no.1
• /
• pp.79-90
• /
• 2014

With the development of modern society, not only have the Internet and e-commerce been progressed but they also made 'consumption patten' diverse. Despite the internet clothing market growth, there is critical a disadvantage, which is consumers is not able to wear the products presented via online pictures. Thus, pictures on the internet are the only information customers can get, which has caused consciousness on the importance of dealing with 'customer review'. In spite of the fact that 'customer review' has undeniably evolved to be one of customers' essential requisites, the research on this subject is very limited. Until now, the studies on the internet shopping consumers' behavior mostly has to do with the features of 'customer review' such as 'a sense of exaggeration', 'usability', 'duality', 'purity', 'professionalism', 'reliability', and the 'similarity', etc.) Therefore, this study categorizes the characteristics of online shopping reviews to 'the number of reviews', 'the article-length', 'the existence of photos', 'the rewards for reviews', 'the contents of the reviews' and 'the freshness of the reviews' and reviews the impact of an features of 'customers' reviews' affecting the internet shopping sales promotion. Moreover, it is to contribute to the marketing strategies of a shopping mall by analyzing consumers' 'purchasing satisfaction', 'the intention of repurchasing', and 'the factors of viral marketing'.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.6
• /
• pp.473-484
• /
• 2013

Shorten URL service is the method of using short URL instead of long URL, it redirect short url to long URL. While the users of microblog increased rapidly, as the creating and usage of shorten URL is convenient, shorten url became common under the limited length of writing on microblog. E-mail, SMS and books use shorten URL well, because of its simplicity. But, there is no relativeness between the most of shorten URLs and their target URLs, user can not expect the target URL. To cover this problem, there is attempts such as changing the shorten URL service name, inserting the information of website into shorten URL, and the usage of shortcode of physical address. However, each ones has the limits, so these are the trouble of automation, relatively long address, and the narrowness of applicable targets. SHRT is complementary to the attempts, as getting the idea from the writing system of Arabic. Though the writing system of Arabic has no vowel alphabet, Arabs have no difficult to understand their writing. This paper proposes SHRT, new method of URL Shortening. SHRT makes user guess the target URL using Relative word of the lowest domain of target URL without vowels.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.120-126
• /
• 2009

As the information age grows rapidly, the amount of digital texts has been increasing as well. It has brought an increasing of visualization case in order to figure out lots of digital texts. Existing visualized design of digital text is merely concentrating on figuration of subject word through adoption of stemming algorithm and word frequency extraction, prominence of meaning of text, and connection in between sentences. So it is a fact that expression of rhythm that can visualize sentimental feeing of digital text was insufficient. Syllable is a phoneme unit that can express rhythm more efficiently. In sentences, syllable is a most basic pronunciation unit in pronouncing word, phase and sentence. On this basis, accent, intonation, length of rhythm factor and others are based on syllable. Sonority, which is most closely associated with definitions of syllable, is expressed through air flow of igniting lung and acoustic energy that is specified kinetic energy into sonority. Seen from this perspective, this study examines phonologic definition and characteristics based on syllable, which is properties of digital text, and research the way to visualize rhythm through diagram. After converting digital text into phonetic symbol by the experiment, rhythm information are visualized into images using degree of resonance, which was started from rhythm in all languages, and using syllable establishment of digital text. By visualizing syllable information, it provides syllable information of digital text and express sentiment of digital text through diagram to assist user's understanding by systematic formula. Therefore, this study is aimed at planning for easy understanding of text's rhythm and realizing visualization of digital text.