• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.49-56
• /
• 1999

In many continuous speech recognition systems based on HMMs, decision tree-based state tying has been used for not only improving the robustness and accuracy of context dependent acoustic modeling but also synthesizing unseen models. To construct the phonetic decision tree, standard method performs one-level pruning using just single Gaussian triphone models. In this paper, two novel approaches, two-level decision tree and multi-mixture decision tree, are proposed to get better performance through more accurate acoustic modeling. Two-level decision tree performs two level pruning for the state tying and the mixture weight tying. Using the second level, the tied states can have different mixture weights based on the similarities in their phonetic contexts. In the second approach, phonetic decision tree continues to be updated with training sequence, mixture splitting and re-estimation. Multi-mixture Gaussian as well as single Gaussian models are used to construct the multi-mixture decision tree. Continuous speech recognition experiment using these approaches on BN-96 and WSJ5k data showed a reduction in word error rate comparing to the standard decision tree based system given similar number of tied states.

• MALSORI
• /
• no.43
• /
• pp.179-188
• /
• 2002

Improving the recognition performance of connected digit telephone speech still remains a problem to be solved. As a basic study for it, this paper analyzes the variation of feature parameters of Korean digit telephone speech according to channel distortion. As a feature parameter for analysis and recognition MFCC is used. To analyze the effect of telephone channel distortion depending on each call, MFCCs are first obtained from the connected digit telephone speech for each phoneme included in the Korean digit. Then CMN, RTCN, and RASTA are applied to the MFCC as channel compensation techniques. Using the feature parameters of MFCC, MFCC+CMN, MFCC+RTCN, and MFCC+RASTA, variances of phonemes are analyzed and recognition experiments are done for each case. Experimental results are discussed with our findings and discussions

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.201-207
• /
• 2004

This paper is a study on the recognition of continuous speech and uses a method of speech recognition using syntactic analysis and one-stage DMS/DP. In order to perform the speech recognition, first of all, we make DMS model by section division algorithm and let continuous speech data be recognized through One-stage DMS/DP method using syntactic analysis. Besides the speech recognition experiments of proposed method, we experiment the conventional one-stage DP method under the equivalent environment of data and conditions. From the recognition experiments, it is shown that Ole-stage DMS/DP using syntactic analysis is superior to conventional method.

• MALSORI
• /
• no.49
• /
• pp.107-121
• /
• 2004

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon to improve the performance of a Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished phonological rules that can be applied to phonemes in within-morpheme and cross-morpheme. The results of 33K-morpheme Korean CSR experiments show that an absolute reduction of 1.45% in WER from the baseline performance of 18.42% WER was achieved by modeling proposed pronunciation variations with a possible multiple context-dependent pronunciation lexicon.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.327-329
• /
• 2007

This paper presents a FSN-based LVCSR system and it's application to the speech TV program guide. Unlike the most popular statistical language model-based system, we used FSN grammar based on the graph theory-based FSN optimization algorithm and knowledge-based advanced word boundary modeling. For the memory and latency efficiency, we implemented the dynamic pruning scheduling based on the histogram of active words and their likelihood distribution. We achieved a 10.7% word accuracy improvement with 57.3% speedup.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.75-78
• /
• 2003

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon for Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished pronunciation variation rules according to the locations such as within a morpheme, across a morpheme boundary in a compound noun, across a morpheme boundary in an eojeol, and across an eojeol boundary. In 33K-morpheme Korean CSR experiment, an absolute improvement of 1.16％ in WER from the baseline performance of 23.17％ WER is achieved by modeling cross-morpheme pronunciation variations with a context-dependent multiple pronunciation lexicon.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.4
• /
• pp.74-81
• /
• 1995

This paper describes the development of speech databases for the Korean language which were constructed at Communications Research Laboratory in KAIST. The procedure and environment to construct the speech database are presented in detail, and the phonetic and linguistic properties of the databases are presented. the databases were intended for use in designing and evaluating speech recognition algorithms. The databases consist of five different sets of speech contents : trade-related continuous speech with 3,000 words, variable-length connected digits, phoneme-balanced 75 isolated words, 500 isolated Korean provincial names, and Korean A-set words.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1995.06a
• /
• pp.228-231
• /
• 1995

반연속 HMM 음성인식 시스템의 화자 적응 성능 향상을 위해 코드북 변환 알고리즘을 제안하였다. 기존의 화자 적응 알고리즘으로는 새로운 화자의 적응 데이터 특징의 분포와 HMM 모수의 사전밀도를 함께 고려하는 베이시안 화자적응 알고리즘이 있다. 그러나 새로운 화자의 특징분포와 코드북 사전 밀도의 차이가 큰 경우 적응 데이터와 코드북간의 잘못된 대응 관계를 얻을 수 있으며, 기준 코드북에 필요 이상으로 많은 코드워드가 존재하는 경우 적응된 코드북에도 불필요한 코드워드 들이 남아 인식 과정에 혼란을 줄 수 있다. 이 문제점을 해결하기 위하여 제안된 코드북 변환 알고리즘에서는 주파수 영역의 포만트 정보를 이용하였다. 화자 적응을 수행하기 앞서 코드북의 켑스트럼으로부터 포만트를 추출해 내고, 이들의 분포를 적응 화자의 포만트 분포와 일치되도록 변환시켜 주었다. 이 변환된 포만트들로부터 다시 켑스트럼을 구하여 변환된 코드북을 얻고 이를 화자 적응의 초기 코드북으로 사용하였다. 제안된 알고리즘을 이용하였을 경우 코드북과 적응 화자의 음성 간의 정확한 대응관계를 찾을 수 있었고, 불필요한 코드워드들이 인식 과정에서 사용되지 않도록 변환되어 인식률이 향상되는 것을 실험을 통해 확인하였다.

• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.153-157
• /
• 1996

본 논문은 연속 분포 HMM을 사용한 핵심어 추출기법(Keyword Spotting)과 화자 인식에 기반한 음성 다이얼링 및 부서 안내에 관한 것이다. 개발된 시스템은 상대방의 이름, 직책, 존칭 등에 감탄사나 명령어 등이 혼합된 형태의 자연스런 음성 문장으로부터 다이얼링과 안내에 필요한 핵심어를 자동 추출하고 있다. 핵심 단어의 사용에는 자연성을 고려하여 문법적 제약을 최소한으로 두었으며, 각 단어 모델에 대해서는 음소의 갯수 더하기 $3{\sim}4$개의 상태 수와 3개 정도의 mixture component로써 좌우향 모델을, 묵음모델에 대해서는 2개 상태의 ergodic형 모델을 구성하였다. 인식에 있어서는 프레임 동기 One-Pass 비터비 알고리즘과 beam pruning을 채택하였으며, 인식에 사용된 어휘는 36개의 성명, 8개의 직위 및 존칭, 5개 정도의 호출어, 부탁을 나타내는 동사 및 그 활용이 10개 정도이다. 약 $3{\sim}6$개 정도의 단어로 구성된 문장을 실시간($1{\sim}3$초이내)에 인식하고, 약 98% 정도의 핵심어 인식 성능을 나타내고 있다.