• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2002년도 11월 학술대회지
• /
• pp.201-204
• /
• 2002

As a preliminary study for improving recognition performance of the connected digit telephone speech, we investigate feature parameters as well as channel compensation methods of telephone speech. The CMN and RTCN are examined for telephone channel compensation, and the MFCC, DWFBA, SSC and their delta-features are examined as feature parameters. Recognition experiments with database we collected show that in feature level DWFBA is better than MFCC and for channel compensation RTCN is better than CMN. The DWFBA+Delta_ Mel-SSC feature shows the highest recognition rate.

• 대한음성학회지:말소리
• /
• 제55권
• /
• pp.103-118
• /
• 2005

In this paper, we describe a morpheme-based pronunciation lexicon useful for Korean LVCSR. The phonemic-context-dependent multiple pronunciation lexicon improves the recognition accuracy when cross-morpheme pronunciation variations are distinguished from within-morpheme pronunciation variations. Since adding all possible pronunciation variants to the lexicon increases the lexicon size and confusability between lexical entries, we have developed a lexicon pruning scheme for optimal selection of pronunciation variants to improve the performance of Korean LVCSR. By building a proposed pronunciation lexicon, an absolute reduction of $0.56\%$ in WER from the baseline performance of $27.39\%$ WER is achieved by cross-morpheme pronunciation variations model with a phonemic-context-dependent multiple pronunciation lexicon. On the best performance, an additional reduction of the lexicon size by $5.36\%$ is achieved from the same lexical entries.

• 대한음성학회지:말소리
• /
• 제46호
• /
• pp.77-86
• /
• 2003

Channel distortion and coarticulation effect in the Korean connected digit telephone speech make it difficult to achieve high performance of connected digit recognition in the telephone environment. In this paper, as a basic research to improve the recognition performance of Korean connected digit telephone speech, recognition error patterns are investigated and analyzed. Korean connected digit telephone speech database released by SiTEC and HTK system are used for recognition experiments. Both DWFBA and MRTCN methods are used for feature extraction and channel compensation, respectively. Experimental results are discussed with our findings.

• 음성과학
• /
• 제6권
• /
• pp.181-195
• /
• 1999

This study proposes a method of recognizing postpositions and suffixes in Korean spoken language, using prosodic information. We detect grammatical boundaries automatically at first, by using prosodic information of the accentual phrase, and then we recognize grammatical function words by backward-tracking from the boundaries. The experiment employs 300 sentential speech data of 10 men's and 5 women's voice spoken in standard Korean, in which 1080 accentual phrases and 11 postpositions and suffixes are included. The result shows the recognition rate of postpositions in two cases. In one case in which only correctly detected boundaries are included, the recognition rate is 97.5%, and in the other case in which all detected boundaries are included, the recognition rate is 74.8%.

• 대한음성학회지:말소리
• /
• 제53호
• /
• pp.143-156
• /
• 2005

Speaker adaptation in eigenvoice space is a popular method for rapid speaker adaptation. To improve the performance of the method, the number of speaker dependent models should be increased and eigenvoices should be re-estimated. However, principal component analysis takes much time to find eigenvoices, especially in a continuous speech recognition system. This paper describes a method to reduce computation time to estimate eigenvoices only for supplementary speaker dependent models and to merge them with the used eigenvoices. Experiment results show that the computation time is reduced by 73.7% while the performance is almost the same in case that the number of speaker dependent models is the same as used ones.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 10월 학술대회지
• /
• pp.145-148
• /
• 2003

To improve the recognition performance of Korean connected digit telephone speech, in this paper, both Aurora feature extraction method that employs noise reduction 2-state Wiener filter and DWFBA method are investigated and used. CMN and MRTCN are applied to static features for channel compensation. Telephone digit speech database released by SITEC is used for recognition experiments with HTK system. Experimental results has shown that Aurora feature is slightly better than MFCC and DWFBA without channel compensation. And when channel compensation is included, Aurora feature is slightly better than DWFBA with MRTCN.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.103-106
• /
• 2005

In this paper, we propose a language modeling approach to improve the performance of a large vocabulary continuous speech recognition system. The proposed approach is based on the active learning framework that helps to select a text corpus from a plenty amount of text data required for language modeling. The perplexity is used as a measure for the corpus selection in the active learning. From the recognition experiments on the task of continuous Korean speech, the speech recognition system employing the language model by the proposed language modeling approach reduces the word error rate by about 6.6 % with less computational complexity than that using a language model constructed with randomly selected texts.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.83-86
• /
• 2003

This paper presents our style-based language model adaptation for Korean conversational speech recognition. Korean conversational speech is observed various characteristics of content and style such as filled pauses, word omission, and contraction as compared with the written text corpora. For style-based language model adaptation, we report two approaches. Our approaches focus on improving the estimation of domain-dependent n-gram models by relevance weighting out-of-domain text data, where style is represented by n-gram based tf*idf similarity. In addition to relevance weighting, we use disfluencies as predictor to the neighboring words. The best result reduces 6.5％ word error rate absolutely and shows that n-gram based relevance weighting reflects style difference greatly and disfluencies are good predictor.

• 한국음향학회지
• /
• 제21권7호
• /
• pp.656-664
• /
• 2002

본 논문에서는 한국어 발음열 자동 생성기를 이용하여 한국어의 음운 규칙에 대한 통계적 분석을 수행하였다. 실험에 사용한 발음열 자동 생성기는 한국어 음운 변화 현상에 대해 형태음운론에 기반 한 언어학적 분석과 문교부 표준어 규정의 표준 발음법에서 유도된 필수 및 수의적 음소 변동 규칙과 변이음 규칙의 단계적 적용 모델을 사용해서 구현되었으며, 특히 연속음성 인식을 위한 학습용 발음열과 인식용 발음사전 생성의 최적화를 목표로 하였다. 본 논문에서는 대어휘 연속음성 인식기의 음향 모델을 구축하기 위해 만들어진 삼성 PBS(Phonetically Balanced Sentence) 음성 데이터 베이스의 60,000문장에 적용된 발음열 생성기의 음소 변동규칙들의 분포 및 그 통계를 사용해서 한국어 음운 변화 양상을 분석하였다. 적용된 빈도수를 기준으로 분석한 결과, 필수음소 변동규칙의 경우는 연음법칙, 경음화, 격음화, 장애음의 비음화순으로, 수의적 음소 변동규칙의 경우는 초성 ㅎ 탈락, 중복 자음화, 동일 조음위치 자음탈락 순으로 음운 변화가 발생하였다. 이러한 적용 규칙들의 통계적 자료를 기반으로 한국어 음운 변화 양상을 파악할 수 있었으며, 나아가 본 논문의 연구 결과는 음성 인식 시스템을 개발하는데 유용하게 사용할 수 있을 것이다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2015년도 제51차 동계학술대회논문집 23권1호
• /
• pp.209-212
• /
• 2015

LTE-Advanced 망을 형성하는 리소스 및 망의 형상(대역, 에러율 등)들은 가변적으로 변하기 때문에 기존 음성 서비스에 적용된 절차적이고, 인위적이고, 정적인 제어방식으로는 제어가 불가능한 것으로 인식되고 있다. 본 연구에서는 정책 제어를 기반으로 서비스 연속성을 효과적으로 지원하기 위한 QoS 관리 체계를 제안하고자 한다. 제안되는 QoS 관리 체계에서는 가입자 단말기는 자신의 현재 상태 및 주변 기지국 정보를 수집하고, 기지국은 내부 및 인접한 기지국 모니터링으로 정보를 수집한다. 또한 이와 같은 관련 제어 데이터를 공유하고 이를 종합 분석하여 서비스 연속성을 자체적으로 제어할 수 있게 한다.