Speech recognition expert system : an integration of knowledge-based system and neural networks
この論文にアクセスする
この論文をさがす
著者
書誌事項
- タイトル
-
Speech recognition expert system : an integration of knowledge-based system and neural networks
- 著者名
-
小森, 康弘
- 著者別名
-
コモリ, ヤスヒロ
- 学位授与大学
-
早稲田大学
- 取得学位
-
博士 (工学)
- 学位授与番号
-
乙第933号
- 学位授与年月日
-
1993-02-12
注記・抄録
博士論文
目次
- Contents / p1 (0003.jp2)
- 1 INTRODUCTION / p1 (0006.jp2)
- 1.1 Speech Communication / p1 (0006.jp2)
- 1.2 Background / p2 (0007.jp2)
- 1.3 Purpose / p6 (0009.jp2)
- 1.4 Contents / p7 (0009.jp2)
- 2 SPEECH RECOGNITION EXPERT SYSTEM / p9 (0010.jp2)
- 2.1 Introduction / p9 (0010.jp2)
- 2.2 Spectrogram Reading / p9 (0010.jp2)
- 2.3 Conventional Approach and Problems / p12 (0012.jp2)
- 2.4 Expert System / p13 (0012.jp2)
- 2.5 Components / p14 (0013.jp2)
- 2.6 Tables&Figures / p24 (0018.jp2)
- 3 EXPERT SYSTEM IMPLEMENTATION / p27 (0019.jp2)
- 3.1 Introduction / p27 (0019.jp2)
- 3.2 System Configuration / p27 (0019.jp2)
- 3.3 Vowel / p28 (0020.jp2)
- 3.4 Consonant / p29 (0020.jp2)
- 3.5 Integration Mechanisms / p35 (0023.jp2)
- 3.6 Recognition Example / p39 (0025.jp2)
- 3.7 Tables & Figures / p40 (0026.jp2)
- 4 SYSTEM EVALUATION / p53 (0032.jp2)
- 4.1 Introduction / p53 (0032.jp2)
- 4.2 Database / p53 (0032.jp2)
- 4.3 Acoustic Analysis / p54 (0033.jp2)
- 4.4 Vowel Detection Experiment / p54 (0033.jp2)
- 4.5 Consonant Recognition Experiment / p55 (0033.jp2)
- 4.6 Comparison of Integration Mechanisms / p58 (0035.jp2)
- 4.7 All Phoneme Recognition Experiment / p59 (0035.jp2)
- 4.8 Conclusion / p61 (0036.jp2)
- 4.9 Tables&Figures / p64 (0038.jp2)
- 5 ROBUSTNESS OF FEATURE BASED SEGMENTATION / p69 (0040.jp2)
- 5.1 Introduction / p69 (0040.jp2)
- 5.2 Rule Expansion / p70 (0041.jp2)
- 5.3 Segmentation Experiment / p70 (0041.jp2)
- 5.4 Conclusion / p73 (0042.jp2)
- 5.5 Tables&Figures / p74 (0043.jp2)
- 6 TIME-STATE NEURAL NETWORKS / p81 (0046.jp2)
- 6.1 Introduction / p81 (0046.jp2)
- 6.2 Time-State Neural Networks / p82 (0047.jp2)
- 6.3 Experiment Using TDNN and TSNNs / p84 (0048.jp2)
- 6.4 Conclusion / p86 (0049.jp2)
- 6.5 Tables&Figures / p87 (0049.jp2)
- 7 NEURAL FUZZY TRAINING / p91 (0051.jp2)
- 7.1 Introduction / p91 (0051.jp2)
- 7.2 Neural Fuzzy Training / p93 (0052.jp2)
- 7.3 Phoneme Identification Experiment / p94 (0053.jp2)
- 7.4 Continuous Speech Recognition Experiment / p96 (0054.jp2)
- 7.5 Conclusion / p102 (0057.jp2)
- 7.6 Tables&Figures / p103 (0057.jp2)
- 8 CONCLUSIONS / p113 (0062.jp2)
- 8.1 Summary / p113 (0062.jp2)
- 8.2 Further Research / p117 (0064.jp2)
- A Typical Segmentation Knowledge / p119 (0065.jp2)
- B Multiple Speaker Speech Segmentation / p137 (0074.jp2)