• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.267-283
• /
• 2023

The COVID-19 pandemic, which began in December 2019 and continues to this day, has left the public needing information to help them cope with the pandemic. However, COVID-19-related fake news on social media seriously threatens the public's health. In particular, if fake news related to COVID-19 is massively spread with similar content, the time required for verification to determine whether it is genuine or fake will be prolonged, posing a severe threat to our society. In response, academics have been actively researching intelligent models that can quickly detect COVID-19-related fake news. Still, the data used in most of the existing studies are in English, and studies on Korean fake news detection are scarce. In this study, we collect data on COVID-19-related fake news written in Korean that is spread on social media and propose an intelligent fake news detection model using it. The proposed model utilizes the frequency information of parts of speech, one of the linguistic characteristics, to improve the prediction performance of the fake news detection model based on Doc2Vec, a document embedding technique mainly used in prior studies. The empirical analysis shows that the proposed model can more accurately identify Korean COVID-19-related fake news by increasing the recall and F1 score compared to the comparison model.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.7
• /
• pp.390-395
• /
• 2011

This paper covers the studies on common voice parameters through the voice analysis of female main news anchors on weekday evening by the station, and differences of relative voices and sounds among stations. To examine voice characteristics, 6 voice parameters were analyzed and it showed anchors of each station had distinctive characteristics of voices and phonations over all fields except the speech rate, and there were also differences in sound systems. As major analysis parameters, basic pitch, tone of the 1st formant and pitch ratio, level of closeness by pitch bandwidth, type of sentence closing through average pitch position within pitch bandwidth, average speech rate, and acoustic tone analysis by energy distribution by frequency band were used. Analyzed values and results could be referred to and utilized in the criteria of phonation characteristics for domestic female news anchors.

• MALSORI
• /
• no.56
• /
• pp.207-223
• /
• 2005

The goal of language model adaptation is to improve the background language model with a relatively small adaptation corpus. This study presents a language model adaptation technique where additional text data for the adaptation do not exist. We propose the information retrieval (IR) technique with N-gram language modeling to collect the adaptation corpus from baseline text data. We also propose to use a dynamic language model interpolation coefficient to combine the background language model and the adapted language model. The interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech data reserved for held-out validation data. This allows the final adapted model to improve the performance of the background model consistently The proposed approach reduces the word error rate by $13.6\%$ relative to baseline 4-gram for two-hour broadcast news speech recognition.

• Phonetics and Speech Sciences
• /
• v.13 no.3
• /
• pp.65-70
• /
• 2021

This paper proposes a method for designing a large recording script for open domain English speech synthesis. For read-aloud style text, 12 domains and 294 sub-domains were designed using text contained in five different news media publications. For conversational style text, 4 domains and 36 sub-domains were designed using movie subtitles. The final script consists of 43,013 sentences, 27,085 read-aloud style sentences, and 15,928 conversational style sentences, consisting of 549,683 tokens and 38,356 types. The completed script is analyzed using four criteria: word coverage (type coverage and token coverage), high-frequency vocabulary coverage, phonetic coverage (diphone coverage and triphone coverage), and readability. The type coverage of our script reaches 36.86% despite its low token coverage of 2.97%. The high-frequency vocabulary coverage of the script is 73.82%, and the diphone coverage and triphone coverage of the whole script is 86.70% and 38.92%, respectively. The average readability of whole sentences is 9.03. The results of analysis show that the proposed method is effective in producing a large recording script for English speech synthesis, demonstrating good coverage in terms of unique words, high-frequency vocabulary, phonetic units, and readability.

• MALSORI
• /
• no.51
• /
• pp.99-115
• /
• 2004

In this parer, we propose LM adaptation for broadcast news recognition. We collect information of recent articles from the internet on real time, make a recent small size LM, and then interpolate recent LM with a existing LM composed of existing large broadcast news corpus. We performed interpolation experiments to get the best type of articles from recent corpus because collected recent corpus is composed of articles which are related with test set, and which are unrelated. When we made an adapted LM using recent LM with similar articles to test set through Tf-Idf method and existing LM, we got the best result that ERR of pseudo-morpheme based recognition performance has 17.2 % improvement and the number of OOV has reduction from 70 to 27.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.197-200
• /
• 2007

The purpose of this study is to analyze the prosodic characteristics of Korean news utterances. In this paper, prosodic phrases were described in terms of the K-ToBI labeling system. In addition, the change of intonation contour that occurs throughout the sentences was discussed in terms of types of media and gender. According to analyzing the tendency of resets, 331 out of 729 resets were observed at the boundary of the intonation phrases. This means that resets are of the speaker's own volition regardless of prosodic units of intonation phrases. The declination of the intonation contour of radio news showed a gentler slope than that of TV news, because when the sentence is getting longer, the declination of the intonation contour becomes slower.

• The Journal of the Korea Contents Association
• /
• v.20 no.2
• /
• pp.499-510
• /
• 2020

This study aims to analyze the causes of Internet hate speech, which has recently been emerging as a serious social problem and to seek for countermeasures. The experiences of hate speech are examined through the analysis of college students' essays and the causes and solutions of hate speech are suggested through the in-depth interviews with the experts. College students experience hate speech on the Internet on the basis of attributes such as age, gender, sexual orientation, and regionalism. Online comments on news, social media and online games are the main sources in spreading hate speech. On a personal level the lack of awareness of human dignity and the absence of media education are diagnosed as the reasons for online hate speech. The social reasons for online hate speech lie in the lack of human rights education and the problems of the media. In order to improve the problems of Internet hate speech, various suggestions are proposed on the legal, social and educational levels.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.465-473
• /
• 2017

An experiment was conducted to investigate the relationship between the DVEs and subtitles provided with anchor speech in TV news and the news evaluation, trust and agenda recognition. 120 university students were asked to watch four types of news that differed in the contents of their DVEs and subtitles, and then they evaluated the fairness, sensibility, and irritability of the news. The content of DVEs and subtitles were related to the irritability evaluation and trust of the news, and it was not related with the fairness and sensibility evaluation. When the DVEs and subtitles emphasizing the stimulating aspects of the issue were given, the irritability was highly evaluated and the trust was low. The evaluation on news fairness affected the news trust. The more they rated news as fair, the greater the trust in news. Unlike the assumption in this study, DVEs and subtitles were not the main factors influencing the news agenda perception, and the viewers tended to perceive the agenda based on the news content itself.

• Proceedings of the KSPS conference
• /
• 1996.10a
• /
• pp.472-472
• /
• 1996

The material of database for speech recognition should include phonetic phenomena as much as possible. At the same time, such material should be phonetically compact with low redundancy[1, 2]. The phonetic phenomena in continuous speech is the key problem in speech recognition. This paper describes the processing of a set of sentences collected from the database of 1993 and 1994 "People's Daily"(Chinese newspaper) which consist of news, politics, economics, arts, sports etc.. In those sentences, both phonetic phenometla and sentence patterns are included. In continuous speech, phonemes always appear in the form of allophones which result in the co-articulary effects. The task of designing a speech database should be concerned with both intra-syllabic and inter-syllabic allophone structures. In our experiments, there are 404 syllables, 415 inter-syllabic diphones, 3050 merged inter-syllabic triphones and 2161 merged final-initial structures in read speech. Statistics on the database from "People's Daily" gives and evaluation to all of the possible phonetic structures. In this sentence set, we first consider the phonetic balances among syllables, inter-syllabic diphones, inter-syllabic triphones and semi-syllables with their junctures. The syllabic balances ensure the intra-syllabic phenomena such as phonemes, initial/final and consonant/vowel. the rest describes the inter-syllabic jucture. The 1560 sentences consist of 96% syllables without tones(the absent syllables are only used in spoken language), 100% inter-syllabic diphones, 67% inter-syllabic triphones(87% of which appears in Peoples' Daily). There are rougWy 17 kinds of sentence patterns which appear in our sentence set. By taking the transitions between syllables into account, the Chinese speech recognition systems have gotten significantly high recognition rates[3, 4]. The following figure shows the process of collecting sentences. [people's Daily Database] -> [segmentation of sentences] -> [segmentation of word group] -> [translate the text in to Pin Yin] -> [statistic phonetic phenomena & select useful paragraph] -> [modify the selected sentences by hand] -> [phonetic compact sentence set]

• Phonetics and Speech Sciences
• /
• v.8 no.2
• /
• pp.31-39
• /
• 2016

In emergency dispatching at 119 Command & Dispatch Center, some inconsistencies between the 'standard emergency aid system' and 'dispatch protocol,' which are both mandatory to follow, cause inefficiency in the dispatcher's performance. If an emergency dispatch system uses automatic speech recognition (ASR) to process the dispatcher's protocol speech during the case registration, it instantly extracts and provides the required information specified in the 'standard emergency aid system,' making the rescue command more efficient. For this purpose, we have developed a Korean large vocabulary continuous speech recognition system for 400,000 words to be used for the emergency dispatch system. The 400,000 words include vocabulary from news, SNS, blogs and emergency rescue domains. Acoustic model is constructed by using 1,300 hours of telephone call (8 kHz) speech, whereas language model is constructed by using 13 GB text corpus. From the transcribed corpus of 6,600 real telephone calls, call logs with emergency rescue command class and identified major symptom are extracted in connection with the rescue activity log and National Emergency Department Information System (NEDIS). ASR is applied to emergency dispatcher's repetition utterances about the patient information. Based on the Levenshtein distance between the ASR result and the template information, the emergency patient information is extracted. Experimental results show that 9.15% Word Error Rate of the speech recognition performance and 95.8% of emergency response detection performance are obtained for the emergency dispatch system.