• Title/Summary/Keyword: tying

Search Result 170, Processing Time 0.025 seconds

Retrieve System for Performance support of Vocabulary Clustering Model In Continuous Vocabulary Recognition System (연속 어휘 인식 시스템에서 어휘 클러스터링 모델의 성능 지원을 위한 검색 시스템)

  • Oh, Sang Yeob
    • Journal of Digital Convergence
    • /
    • v.10 no.9
    • /
    • pp.339-344
    • /
    • 2012
  • Established continuous vocabulary recognition system improved recognition rate by using decision tree based tying modeling method. However, since system model cannot support the retrieve of phoneme data, it is hard to secure the accuracy. In order to improve this problem, we remodeled a system that could retrieve probabilistic model from continuous vocabulary clustering model to phoneme unit. Therefore in this paper showed 95.88%of recognition rate in system performance.

Performance Comparison of Acoustic Modeling Technique (음소 모델링 방식들의 성능 비교)

  • 송명규
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • 1998.06e
    • /
    • pp.377-380
    • /
    • 1998
  • HMM 기반의 음성 인식기를 구현하는데 있어서 모델의 복잡도와 제한된 훈련 데이터 사이의 균형을 유지하는 것은 중요한 문제이다. 중간규모 또는 대용량 어휘 인식 시스템은 정교한 모델을 얻기 위해서 문맥종속 음소 모델링이 필수적이다. 그러나, 제한된 훈련 데이터로는 발생 가능한 모든 context를 포함하기가 어렵고, 더구나 훈련 데이터에서 관찰된 context중에서도 그 관찰빈도가 낮은 것이 많아서 신뢰성 있는 문맥종속 모델들을 얻기에는 여전히 어려움이 따른다. 또한 경우에 따라서는 계산량의 감축을 위하여 모델 규모를 축소시킬 필요도 생긴다. 이러한 문제를 해결하기 위해 본 논문에서는 unit reduction 방법들과 state tying을 이용한 방법들의 성능을 실험을 통해 비교한다. 고립단어 인식 실험결과 state tying을 이용한 방법이 unit reduction에 비하여 우수함을 확인 할 수 있었다.

  • PDF

Geometry-dependent MITC method for a 2-node iso-beam element

  • Lee, Phill-Seung;Noh, Hyuk-Chun;Choi, Chang-Koon
    • Structural Engineering and Mechanics
    • /
    • v.29 no.2
    • /
    • pp.203-221
    • /
    • 2008
  • In this paper, we present an idea of the geometry-dependent MITC method. The simple concept is exemplified to improve a 2-node iso-beam (isoparametric beam) finite element of varying section. We first study the behavior of a standard 2-node iso-beam finite element of prismatic section, which has been widely used with reduced integration (or the equivalent MITC method) in order to avoid shear locking. Based on analytical studies on cantilever beams of varying section, we propose the axial strain correction (ASC) scheme and the geometry-dependent tying (GDT) scheme for the 2-node iso-beam element. We numerically analyze varying section beam problems and present the improved performance by using both ASC and GDT schemes.

Knot Tying & Pushing

  • Yu, Jae-Cheol
    • The Academic Congress of Korean Shoulder and Elbow Society
    • /
    • 2005.11a
    • /
    • pp.214-217
    • /
    • 2005
  • PDF

Minimal Medial-row Tie with Suture-bridge Technique for Medium to Large Rotator Cuff Tears

  • Lee, Hyun Il;Ryu, Ho Young;Shim, Sang-Jun;Yoo, Jae Chul
    • Clinics in Shoulder and Elbow
    • /
    • v.18 no.4
    • /
    • pp.197-205
    • /
    • 2015
  • Background: The purpose of this study was to evaluate the postoperative magnetic resonance imaging (MRI) results of minimal-tying (one medial-row tie among 4 medial-row sutures) on the medial-row in double-row suture-bridge configuration ($2{\times}2$ anchor with $4{\times}4$ suture stands). Methods: From 2011 March to 2012 July, 79 patients underwent arthroscopic rotator cuff repair using $2{\times}2$ anchor double-row configuration. The mean age was 61.3 years (range, 31-81 years). Two double-loaded suture anchors were used for medial-row. Four medial-row stitches were made with only one medial-row knot-tying (the most anterior suture). Lateral-row was secured using the conventional suture-bridge anchor technique; all 4 strands were used for each anchor. Repair integrity was evaluated with MRI at mean 6.2 months postoperatively. Retear and the pattern of retear, change of fatty infiltration, and muscle atrophy of supraspinatus were evaluated using pre- and postoperative MRI. Results: Repaired tendon integrity was 38 for type I, 30 for type II, 6 for type III, 4 for type IV, and 1 for type V, according to Sugaya classification. Considering type IV/V as retear, the rate was 6.3% (5 out of 79 patients). Medial cuff failure was observed in 4 patients. Fatty atrophy of supraspinatus was significantly improved postoperatively according to Goutallier grading (p=0.01). The level of muscle atrophy of supraspinatus was not changed significantly after surgery. Conclusions: Minimal tying technique with suture configuration of four-by-four strand double-row suture-bridge yielded a lower retear rate (6.3%) in medium to large rotator cuff tears.

Minimally Invasive Techniques for the Treatment of Mucoceles in Young Patients: A Case Series (소아환자의 점액종 치료 시 최소침습적 방법: 증례 보고)

  • Kim, Jongsung;Kim, Gimin;Lee, Jaesik;Kim, Hyunjung;Nam, Soonhyeun
    • Journal of the korean academy of Pediatric Dentistry
    • /
    • v.49 no.1
    • /
    • pp.113-120
    • /
    • 2022
  • Oral mucocele is a common exophytic lesion resulting from the accumulation of saliva due to pathological changes in the minor salivary glands. It is typically asymptomatic and painless and characterized by semipermeable, fluctuant nodules. General treatment methods for mucocele include surgical excision, marsupialization, cryosurgery, and steroid injection. This case report presents the treatment of oral mucocele using micro-marsupialization and a tying method as minimally invasive techniques rather than surgical treatment. Based on this case report, it is suggested that micro-marsupialization and the tying method can be used as alternative methods for the treatment of oral mucocele infants and children with behavioral control problems.

Improved Decision Tree-Based State Tying In Continuous Speech Recognition System (연속 음성 인식 시스템을 위한 향상된 결정 트리 기반 상태 공유)

  • ;Xintian Wu;Chaojun Liu
    • 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.

  • PDF