• Speech Sciences
• /
• v.3
• /
• pp.119-131
• /
• 1998

We have developed a keyword spotting system for automatic speech editing. This system recognizes the only keyword 'MBC news' and then sends the time information to the host system. We adopted a vocabulary dependent model based on continuous hidden Markov model, and the Viterbi search was used for recognizing the keyword. In recognizing the keyword, the system uses a parallel network where HMM models are connected independently and back-tracking information for reducing false alarms and missing. We especially focused on implementing a stable and practical real-time system.

• Proceedings of the KSPS conference
• /
• 2006.05a
• /
• pp.85-88
• /
• 2006

Generally the news subtitle is considered as be free of fault. But actually it has committed a fault in many respects. Among these I made a special study of phonological faults; alternation of graphemes, insertion of graphemes, deletion of graphemes and the orthography of loanwords. It is very surprising that the news subtitle has many faults against Korean orthography, We must try to get rid of the faults in the news subtitle.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.33-36
• /
• 2002

We implemented a robust Korean broadcast news transcription system for out-of-vocabulary (OOV), tested its performance. The occurrence of OOV words in the input speech is inevitable in large vocabulary continuous speech recognition (LVCSR). The known vocabulary will never be complete due to the existence of for instance neologisms, proper names, and compounds in some languages. The fixed vocabulary and language model of LVCSR system directly face with these OOV words. Therefore our Broadcast news recognition system has an offline OOV update module of language model and vocabulary to solve OOV problem and selects morpheme-based recognition unit (so called, pseudo-morpheme) for OOV robustness.

• Speech Sciences
• /
• v.8 no.1
• /
• pp.77-91
• /
• 2001

This paper investigates the timing of Korean spoken in a news-reading speech style in order to improve the naturalness of durations used in Korean speech synthesis. Each segment in a corpus of 671 read sentences was annotated with 69 segmental and prosodic features so that the measured duration could be correlated with the context in which it occurred. A CART model based on the features showed a correlation coefficient of 0.79 with an RMSE (root mean squared prediction error) of 23 ms between actual and predicted durations in reserved test data. These results are comparable with recent published results in Korean and similar to results found in other languages. An analysis of the classification tree shows that phrasal structure has the greatest effect on the segment duration, followed by syllable structure and the manner features of surrounding segments. The place features of surrounding segments only have small effects. The model has application in Korean speech synthesis systems.

• MALSORI
• /
• no.61
• /
• pp.101-111
• /
• 2007

A modified speech recogniser have been proposed for automatic capitalisation generation to improve the readability of English speech recognition output. In this modified speech recogniser, every word in its vocabulary is duplicated: once in a de-caplitalised form and again in the capitalised forms. In addition its language model is re-trained on mixed case texts. In order to evaluate the performance of the proposed system, experiments of automatic capitalisation generation were performed for 3 hours of Broadcast News(BN) test data using the modified HTK BN transcription system. The proposed system produced an F-measure of 0.7317 for automatic capitalisation generation with an SER of 48.55, a precision of 0.7736 and a recall of 0.6942.

• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.9-16
• /
• 2006

In this paper, the acoustic model output of CSR(Continuous Speech Recognition) was used to analyze news data News database used in this experiment was consisted of 2,093 articles. Due to the low efficiency of language model, conventional Korean CSR is not appropriate to the analysis of news data. This problem could be handled successfully by introducing post-processing work of recognition result of acoustic model. The acoustic model more robust than language model in Korean environment. The result of post-processing work was made into KIF(Keyword information file). When threshold of acoustic model's output level was 100, 86.9% of whole target morpheme was included in post-processing result. At the same condition, applying length information based normalization, 81.25% of whole target morpheme was recognized. The purpose of normalization was to compensate long-length morpheme. According to experiment result, 75.13% of whole target morpheme was recognized KIF(314MB) had been produced from original news data(5,040MB). The decrease rate of absolute information met was approximately 93.8%.

• Journal of Contemporary Eastern Asia
• /
• v.18 no.2
• /
• pp.68-89
• /
• 2019

When comparing media freedom in Malaysia, Myanmar, and Thailand, so-called "fake news" appears as threats to a deliberative (online) public sphere in these three diverse contexts. However, "racist propaganda", "information operations" and "negative campaigning" might be more accurate terms that explain these forms of systematic manipulative political communication. The three cases show forms of disinformation in under-researched contexts and thereby expand the often Western focused discourses on hate speech and fake news. Additionally, the analysis shows that harmful disinformation disseminated online originates from differing contextual trajectories and is not an "online phenomenon". Drawing on an analysis of connotative context factors, this explorative comparative study enables an understanding of different forms of harmful disinformation in Malaysia, Myanmar, and Thailand. The connotative context factors were inductively inferred from 32 expert interviews providing explanations for the formation of political communication (control) mechanisms.

• Proceedings of the KSPS conference
• /
• 2005.11a
• /
• pp.155-158
• /
• 2005

Keyword spotting is effective to find keyword from the continuously pronounced speech. However, non-keyword may be accepted as keyword when the environmental noise occurs or speaker changes. To overcome this performance degradation, utterance rejection techniques using confidence measure on the recognition result have been developed. In this paper, we apply DTW to the HMM based broadcasting news keyword spotting system for rejecting non-keyword. Experimental result shows that false acceptance rate is decreased to 50%.

• MALSORI
• /
• no.64
• /
• pp.15-37
• /
• 2007

The purpose of this paper is to examine the change of the times on the transmission rate of broadcast message. In order to find out the research results, I collected past recorded news tapes and selected 22 radio news out from era of Japanese Imperialism, 1950's, 1960's and contemporary age. Next I measured each announcer's reading rate, and compared change on news-reading rate between present and past approximately 50 years ago. The results of study with such procedures and methods are as follows : the average reporting rate of newscasters in each era is different. From these results, we can easily grasp diachronic change in the transmission rate of broadcast message. Namely, the results show us that present announcers read news faster than the group of past era of Japanese Imperialism by 68%.

• Phonetics and Speech Sciences
• /
• v.10 no.4
• /
• pp.111-119
• /
• 2018

This paper proposes a method to improve speech recognition performance by extracting various pronunciations of the pseudo-morpheme unit from an eojeol unit corpus and generating a new recognition unit considering pronunciation variations. In the proposed method, we first align the pronunciation of the eojeol units and the pseudo-morpheme units, and then expand the pronunciation dictionary by extracting the new pronunciations of the pseudo-morpheme units at the pronunciation of the eojeol units. Then, we propose a new recognition unit that relies on pronunciation by tagging the obtained phoneme symbols according to the pseudo-morpheme units. The proposed units and their extended pronunciations are incorporated into the lexicon and language model of the speech recognizer. Experiments for performance evaluation are performed using the Korean speech recognizer with a trigram language model obtained by a 100 million pseudo-morpheme corpus and an acoustic model trained by a multi-genre broadcast speech data of 445 hours. The proposed method is shown to reduce the word error rate relatively by 13.8% in the news-genre evaluation data and by 4.5% in the total evaluation data.