The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The Internet has been considerably used as an essential source for health information. A previous study conducted at King Saud bin Abdulaziz University for Health Science (KSAUHS) to assess the quality of online health information in Arabic language has fueled the motivation to establishing a comprehensive trusted health website in the Arabic and English languages. This initiative is called King Abdullah...
This paper investigates unsupervised training strategies for the Korean language in the context of the DGA RAPID Rapmat project. As with previous studies, we begin with only a small amount of manually transcribed data to build preliminary acoustic models. Using the initial models, a larger set of untranscribed audio data is decoded to produce approximate transcripts. We compare both GMM and DNN acoustic...
The current paper presents the articulatory and acoustic results of domain-initial strengthening in Korean language. The simultaneous electropalatographic, electroglottographic, and acoustic signals were recorded and temporally adjusted for alignment. The peak linguopalatal contact, seal duration, contact quotient (CQ) were measured for six Korean consonants at the initial position of five boundary...
In this paper, a new method of compound noun analysis is proposed. It uses decomposition model and unregistered words recognition. The latter contains loanword nouns, name nouns and place name. Loanword noun is recognized based on it's formed by syllables which have low use frequency in Korean syllable. Name noun is recognized based on the characteristics of Korean name and the repeatability of the...
This paper describes challenges and solutions for building a successful voice search system as applied to Japanese and Korean at Google. We describe the techniques used to deal with an infinite vocabulary, how modeling completely in the written domain for language model and dictionary can avoid some system complexity, and how we built dictionaries, language and acoustic models in this framework. We...
When a system is developed, Requirements Document is generated by requirement analysts and then translated to formal specifications by specifiers. If a formal specification can be generated automatically from Natural Language Requirements Document, system development cost and system fault from experts' misunderstanding will be decreased. Also, if we would like to get the higher accuracy in analysis...
This study explains about the Japanese language proficiency index for Koreans using N400 mismatch response. We considered that N400 potential responds to presentation of erroneous grammar of Japanese language in accordance with the learning level of the Japanese language. Japanese and Korean have the same word order of subject, nominative particle and verb, and the nominative particle determines whether...
The Nuclear power plant (NPP) industries in Korea have been making efforts to reduce the human errors which largely contributed to 120 nuclear reactor trips from the year of 2001 to 2006. This study aims to develop a Crew Resource Management (CRM) training program that helps to improve plant performance by reducing the number of the reactor trips caused by the operators' errors. The CRM program was...
Runesinger is a demo of a PC videogame to speak and spell Korean. The player practices a few nouns and verbs by serving food to hungry villagers during a North Korean famine. Inspired by melodic intonation therapy, the player sings a jingle. On each musical note, a ball bounces on an iconic syllable. Through a spelling puzzle, the player composes each syllable in Hangul, which is the phonetic alphabet...
Because people expect better sound reproduction that offers more realistic experience, 3D sound technologies are ceaselessly being improved. When we render 3D sound image using headphones or speakers, the main key of this technology is the Head-related transfer function (HRTF) database. Even though there are various HRTF databases they have some drawbacks such as detrimental effects caused by imperfect...
The verbpsilas properties determine the number and property of the semantic elements under its control. Meanwhile, such properties also confine the projecting position of these elements in syntactic structures. The semantics of a verb is determined by the set of semantic features of its components. In the present article, 23 semantic features are provided, from which a semantic classification tree...
We present a new speech/music discrimination method based on spectral peak feature and spectral peak's duration threshold. The focus is feature extraction that reflects the spectral peak's duration characteristic. Also, we consider fast discrimination and high performance. We extract the spectral peak feature from audio spectrum's each peak track and normalize the feature by length of segment. The...
S-MINDS is a hand held, speech translation engine, which allows an English speaker to communicate with a non-English speaker easily within a question and answer, interview style format. It can handle limited dialogs such as medical triage or hospital admissions. We have been able to build an English-to-Korean medical interviews system in 4 months time. The formal system evaluation indicated a translation...
In this paper, we propose a new speaker change detection algorithm based on spectral peak track analysis. When we pronounce the Korean sentence or words, it has a rhythm and intonation pattern varies according to the kinds of sentence and speaking style. Spectral peak track has relevance to this information and audio data type. Therefore, we use spectral peak track information as a speaker feature...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.