• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.1
• /
• pp.81-88
• /
• 2021

Recently, many videos such as online lecture videos caused by COVID-19 have been generated. However, due to the limitation of working hours and lack of cost, they are only a part of the videos with subtitles. It is emerging as an obstructive factor in the acquisition of information by deaf. In this paper, we try to develop a system that automatically generates subtitles using voice recognition and generates subtitles by separating sentences using the ending and time to reduce the time and labor required for subtitle generation.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.109-117
• /
• 2021

Recently, the use of speech-based interfaces is increasing as a means for human-computer interaction (HCI). Accordingly, interest in post-processors for correcting errors in speech recognition results is also increasing. However, a lot of human-labor is required for data construction. in order to manufacture a sequence to sequence (S2S) based speech recognition post-processor. To this end, to alleviate the limitations of the existing construction methodology, a new data construction method called Back TranScription (BTS) was proposed. BTS refers to a technology that combines TTS and STT technology to create a pseudo parallel corpus. This methodology eliminates the role of a phonetic transcriptor and can automatically generate vast amounts of training data, saving the cost. This paper verified through experiments that data should be constructed in consideration of text style and domain rather than constructing data without any criteria by extending the existing BTS research.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.74-82
• /
• 1995

This paper is study on the voice dialing using HMM and post processing of the connected digits. HMM algorithm is widely used in the speech recognition with a good result. But, the maximum likelihood estimation of HMM(Hidden Markov Model) training in the speech recognition does not lead to values which maximize recognition rate. To solve the problem, we applied the post processing to segmental K-means procedure are in the recognition experiment. Korea connected digits are influenced by the prolongation more than English connected digits. To decrease the segmentation error in the level building algorithm some word models which can be produced by the prolongation are added. Some rules for the added models are applied to the recognition result and it is updated. The recognition system was implemented with DSP board having a TMS320C30 processor and IBM PC. The reference patterns were made by 3 male speakers in the noisy laboratory. The recognition experiment was performed for 21 sort of telephone number, 252 data. The recognition rate was $6\%$ in the speaker dependent, and $80.5\%$ in the speaker independent recognition test.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.401-402
• /
• 2006

음성인식, 합성 및 분석과 같은 음성신호처리 분야에 있어서 기본주파수 즉, 피치를 정확히 검출하는 것은 중요하다. 그러나 포만트의 영향과 천이진폭의 영향 때문에 음성신호에서 피치를 정확히 구하는 것은 매우 어렵다. 더구나 노이즈가 포함된 신호에서는 더 더욱 어려워진다. 따라서 본 논문에서는 켑스트럼영역에서 포만트의 영향 을 제거하고 밴드 필터링 한 후 기본 피치 정보를 강조 보상하여 피치주기를 검출하는 방법을 새로이 제안한다.

• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.379-385
• /
• 1998

한국어가 연속적으로 발음될 때 여러 가지 음운 변동현상이 일어난다. 이것은 한국어 연속음성 인식을 어렵게 하는 주요 요인 중의 한가지이다. 본 논문은 음운변동현상이 반영된 음성 인식 문자열을 규칙에 의거하여 text 기반 문자열로 다시 복원시키고 복원 결과 후보들을 형태소 분석하여 유용한 문자열만을 최종 결과로 생성하게 하는 시스템을 구성하였다. 복원은 4가지 rule 즉, 음절 경계 종성 초성 복원 rule, 모음처리 복원 rule, 끝음절 중성 복원 rule, 한 음절처리 rule에 따라 이루어진다. 규칙 적용 과정중에 효과적인 복원을 위해 x-clustering정보를 정의 하여 사용하고, 형태소 분석기에 입력될 복원 후보수를 제한하기 위해 postfix음절 빈도정보를 구하여 사용한다.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.46-63
• /
• 1995

This thesis described an unlimited vocabulary connected speech recognition system using Time Delay Neural Network(TDNN). The recognition unit is the diphone unit which includes the transition section of two phonemes, and the number of diphone unit is 329. The recognition processing of korean connected speech is composed by three part; the feature extraction section of the input speech signal, the diphone recognition processing and post-processing. In the feature extraction section, the extraction of diphone interval in input speech signal is carried and then the feature vectors of 16th filter-bank coefficients are calculated for each frame in the diphone interval. The diphone recognition processing is comprised by the three stage hierachical structure and is carried using 30 Time Delay Neural Networks. particularly, the structure of TDNN is changed so as to increase the recognition rate. The post-processing section, mis-recognized diphone strings are corrected using the probability of phoneme transition and the probability o phoneme confusion and then the eojeols (Korean word or phrase) are formed by combining the recognized diphones.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.12
• /
• pp.1679-1690
• /
• 2002

This paper, describe about a generation of a syllable restoration regulation for a post processing of a speech recognition and a decrease of a restoration candidate. It created a syllable restoration regulation to create a restoration candidate pronounced with phonetic value recognized through a post processing of the formula system that was a tone to recognize syllable unit phonetic value for a performance enhancement of a dialogue serial speech recognition. Also, I presented a plan to remove a regulation to create unused notation from a real life in a restoration regulation with a plan to reduce number candidate of a restoration meeting. A design implemented a restoration candidate set generator in order a syllable restoration regulation display that it created a proper restoration candidate set. The proper notation meeting that as a result of having proved about a standard pronunciation example and a word extracted from a pronunciation dictionary at random, the notation that an utterance was former was included in proved with what a generation became.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.235-240
• /
• 1994

모음 검출을 통하여 미리 등록한 단어가 아닌 경우에도 화자를 인식할 수 있도록 특징 파라메터를 개발하고, 실용화가 가능하도록 처리 방법을 간략화한 텍스트 독립 화자 인식 연구를 진행하였다. 이를 위해서, 화자가 발성한 음성에서 모음을 검출하여 화자인식에 사용하는 방법을 제안하였으며, 인식은 각 화자가 발성한 음성 신호에서 모음을 검출한 다음, 검출된 모음의 29 채널의 주파수 에너지를 퍼지값으로 효현한 후, 퍼지 추론을 적용하여 수행하였다. 실험을 위해 모음 검출 알고리듬을 개발하였으며, 화자인식의 특징 파라메터로 29 채널 주파수 에너지를 제안하였는데, 별도의 코드북 없이 사용이 가능하고, 기존의 파라메터에 비해 인식율이 높으면서도 구성 및 계산이 간단한 특징이 있다. 실험결과, 미리 작성된 표준패턴과 동일한 단어를 사용한 텍스트 의존 화자 인식 실험은 95.5% 인식율을 보였고, 표준 패턴과 다른 종류의 단어를 사용한 텍스트 독립 화자인식 실험은 94.2% 인식율을 보이고 있다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.482-486
• /
• 2018

본 논문에서는 스마트 스피커 환경에서 음악 재생 발화의 오류를 교정하는 음악 재생 발화 교정 모델을 제안한다. 음악 재생 발화에서 발생하는 다양한 오류 유형을 살펴보고, 음악 재생 발화 교정 모델에 대해 소개한다. 해당 모델은 후보 생성 모델과 교정 판별 모델로 이루어져 있다. 후보 생성 모델은 정답 후보들을 생성하고, 교정 판별 모델은 Random Forest를 사용하여 교정 여부를 판별한다. 제안하는 방법으로 음악 재생 발화에서 실제 사용자 만족도를 높일 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.250-258
• /
• 2007

Current speech recognition technology s achieved high performance with the development of hardware devices, however it is insufficient for some applications where high reliability is required, such as voice control of powered wheelchairs for disabled persons. For the system which aims to operate powered wheelchairs safely by voice in real environment, we need to consider that non-voice commands such as user s coughing, breathing, and spark-like mechanical noise should be rejected and the wheelchair system need to recognize the speech commands affected by disability, which contains specific pronunciation speed and frequency. In this paper, we propose non-voice rejection method to perform voice/non-voice classification using both YIN based fundamental frequency(F0) extraction and reliability in preprocessing. We adopted a multi-template dictionary and acoustic modeling based speaker adaptation to cope with the pronunciation variation of inarticulately uttered speech. From the recognition tests conducted with the data collected in real environment, proposed YIN based fundamental extraction showed recall-precision rate of 95.1% better than that of 62% by cepstrum based method. Recognition test by a new system applied with multi-template dictionary and MAP adaptation also showed much higher accuracy of 99.5% than that of 78.6% by baseline system.