Advanced Machine Learning Applications Based On Speech Recognition Technology/ (Record no. 170531)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 05006namaa22004091i 4500 |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | OSt |
| 005 - أخر تعامل مع التسجيلة | |
| control field | 20250223033422.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 250201s2023 |||a|||f m||| 000 0 eng d |
| 040 ## - CATALOGING SOURCE | |
| Original cataloguing agency | EG-GICUC |
| Language of cataloging | eng |
| Transcribing agency | EG-GICUC |
| Modifying agency | EG-GICUC |
| Description conventions | rda |
| 041 0# - LANGUAGE CODE | |
| Language code of text/sound track or separate title | eng |
| Language code of summary or abstract | eng |
| -- | ara |
| 049 ## - Acquisition Source | |
| Acquisition Source | Deposit |
| 082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 621.382 |
| 092 ## - LOCALLY ASSIGNED DEWEY CALL NUMBER (OCLC) | |
| Classification number | 621.382 |
| Edition number | 21 |
| 097 ## - Degree | |
| Degree | Ph.D |
| 099 ## - LOCAL FREE-TEXT CALL NUMBER (OCLC) | |
| Local Call Number | Cai01.13.08.Ph.D.2023.Ha.A |
| 100 0# - MAIN ENTRY--PERSONAL NAME | |
| Authority record control number or standard number | Hany Ahmed Sayed Mansour, |
| Preparation | preparation. |
| 245 10 - TITLE STATEMENT | |
| Title | Advanced Machine Learning Applications Based On Speech Recognition Technology/ |
| Statement of responsibility, etc. | Hany Ahmed Sayed Mansour ; Supervisors: Prof. Dr. Mohsen A. Rashwan. |
| 246 15 - VARYING FORM OF TITLE | |
| Title proper/short title | /تطبيقات تعلم الآلة المتقدمة بناءً على تقنية التعرف على الكلام |
| 264 #0 - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Date of production, publication, distribution, manufacture, or copyright notice | 2023. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 72 pages : |
| Other physical details | illustrations ; |
| Dimensions | 30 cm. + |
| Accompanying material | CD. |
| 336 ## - CONTENT TYPE | |
| Content type term | text |
| Source | rda content |
| 337 ## - MEDIA TYPE | |
| Media type term | Unmediated |
| Source | rdamedia |
| 338 ## - CARRIER TYPE | |
| Carrier type term | volume |
| Source | rdacarrier |
| 502 ## - DISSERTATION NOTE | |
| Dissertation note | Thesis (Ph.D)-Cairo University, 2023. |
| 504 ## - BIBLIOGRAPHY, ETC. NOTE | |
| Bibliography, etc. note | Bibliography: pages 65-72. |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Based on the nature of the speech recognition systems and their components like <br/>Acoustic modeling and language modeling, we can reuse these components in <br/>different applications and different fields. For example, acoustic modeling can be <br/>replaced by spatial model in the Optical Character Recognition (OCR) problem <br/>and the same language modeling techniques can be used in this case. Another <br/>problem is enhancing the performance of most Error-Correction (EC) algorithms <br/>that operate on genomics reads in the medical field. We can use language <br/>modeling techniques to enhance the performance of these tools. In this thesis, we <br/>are going to present different techniques of speech technologies and how we can <br/>benefit from them in different applications. Firstly, we proposed the OCR system <br/>that can deal with handwritten/typewritten. Secondly, we used language modeling <br/>techniques to automatically tune the performance-sensitive configuration <br/>parameters for EC algorithms. Using N-Gram and Recurrent neural Network <br/>(RNN) language modeling, we validate the intuition that the EC performance can <br/>be computed quantitatively and efficiently. Finally, we proposed a system that <br/>uses semi-supervised techniques to enhance the quality of speech recognition <br/>models. This system competed in an international competition (MGB5) and won <br/>the first place with word Accuracy 63% while the second place was 58%.<br/> |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | بناءً على طبيعة أنظمة التعرف على الكلام ومكوناتها مثل النمذجة الصوتية ونمذجة اللغة، يمكننا إعادة استخدام هذه المكونات في تطبيقات مختلفة ومجالات مختلفة. على سبيل المثال، يمكن استبدال النمذجة الصوتية بالنموذج المكاني في مشكلة التعرف الضوئي على الحروف ويمكن استخدام تقنيات نمذجة اللغة نفسها في هذه الحالة. هناك مشكلة أخرى تتمثل في تحسين أداء معظم خوارزميات تصحيح الخطأEC التي تعمل على قراءة الجينوميات في المجال الطبي. يمكننا استخدام تقنيات النمذجة اللغوية لتحسين أداء هذه الأدوات. في هذه الأطروحة ، سوف نقدم تقنيات مختلفة لتقنيات الكلام وكيف يمكننا الاستفادة منها في تطبيقات مختلفة. أولاً ، اقترحنا نظام التعرف الضوئي على الحروف الذي يمكنه التعامل مع الكتابة اليدوية / المكتوبة على الآلة الكاتبة. ثانيًا ، استخدمنا تقنيات نمذجة اللغة لضبط معلمات التكوين الحساسة للأداء لخوارزميات تلقائيًا. باستخدام نمذجة لغة N-Gram والشبكة العصبية المتكررة، فإننا نتحقق من صحة الحدس القائل بأنه يمكن حساب أداء EC كميًا وفعالًا. أخيرًا ، اقترحنا نظامًا يستخدم تقنيات شبه خاضعة للإشراف لتحسين جودة نماذج التعرف على الكلام. تنافس هذا النظام في مسابقة دولية (MGB5) وفاز بالمركز الأول بدقة كلمة 63٪ بينما كان المركز الثاني 58٪. |
| 530 ## - ADDITIONAL PHYSICAL FORM AVAILABLE NOTE | |
| Issues CD | Issues also as CD. |
| 546 ## - LANGUAGE NOTE | |
| Text Language | Text in English and abstract in Arabic & English. |
| 650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | Communications Engineering |
| Source of heading or term | qrmak |
| 653 #0 - INDEX TERM--UNCONTROLLED | |
| Uncontrolled term | OCR |
| -- | ASR |
| -- | Genomic Language Modeling |
| -- | Spatial Modeling |
| -- | Acoustic Modeling |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Mohsen A. Rashwan |
| Relator term | thesis advisor. |
| 900 ## - Thesis Information | |
| Grant date | 01-01-2023 |
| Supervisory body | Mohsen A. Rashwan |
| Universities | Cairo University |
| Faculties | Faculty of Engineering |
| Department | Department of Electronics and Communications Engineering |
| 905 ## - Cataloger and Reviser Names | |
| Cataloger Name | Aya Mohamed |
| Reviser Names | Huda |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | Dewey Decimal Classification |
| Koha item type | Thesis |
| Edition | 21 |
| Suppress in OPAC | No |
| Source of classification or shelving scheme | Home library | Current library | Date acquired | Inventory number | Full call number | Barcode | Date last seen | Effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | المكتبة المركزبة الجديدة - جامعة القاهرة | قاعة الرسائل الجامعية - الدور الاول | 01.02.2025 | 90053 | Cai01.13.08.Ph.D.2023.Ha.A | 01010110090053000 | 01.02.2025 | 01.02.2025 | Thesis |