پديد آورنده :
ضياالديني، امير
عنوان :
بررسي وطراحي يك سيستم جستجوگر موسيقي مبتني برانحراف پوياي زمان
مقطع تحصيلي :
كارشناسي ارشد
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
ده، 83ص: مصور، جدول، نمودار
يادداشت :
ص.ع. به فارسي وانگليسي
توصيفگر ها :
سيستمQBH , منطبق سازي ملودي , هم ترازي سري هاي زماني , الگوريتم انحراف پوياي زمان , محدوديت هاي سراسري
تاريخ نمايه سازي :
3/8/91
استاد داور :
مهدي برنجكوب، محمدرضايزدچي
تاريخ ورود اطلاعات :
1396/09/20
رشته تحصيلي :
برق وكامپيوتر
دانشكده :
مهندسي برق و كامپيوتر
چكيده فارسي :
به فارسي وانگليسي:قابل رويت درنسخه ديجيتالي
چكيده انگليسي :
Investigation and Design of a Music Searcher System Based on Dynamic Time Warping Amir Ziaeddini a ziaedini@ec iut ac ir Date of Submission 2012 03 11 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisor Dr Behzad Nazari Nazari@cc iut ac ir AbstractToday due to development of information technology and extraordinary growth of data it is necessaryto develop new methods to query this information Music Information Retrieval or music query isone of these challenges Music query based on information such as title composer or genre is possibleusing general search engines today if this information is available But if not searching by directmusical content would be a solution in that case In this thesis Query By Humming QBH systems and the previous researches in this area havebeen studied In these systems the users can search for their favorite song by just whistling or singingpart of the song Since there would be some possible errors due to false whistling the algorithmshould be robust to work in these cases An efficient QBH system must have pitch detector melodyextractor time series aligner and sequence matcher In this study relative pitch frequencies of thenotes have been used to represent the melodies instead of absolute pitch frequencies In this mannerthe system is not sensitive to the beginning note because people may whistle the song on differentclefs or octaves In addition the Rhythm of the melodies has been taken in to account by introducing anew criterion named IoIRatio This criterion is robust to Tempo i e in order to obtain an efficientmusic retrieval the IoIRatio assists the system to tolerate the errors originated from different temposbetween the whistled query and the original song in the database Moreover Dynamic Time Warping DTW algorithm that is based on Dynamic Programming has been employed to match the query anddatabase songs and also to measure the similarity between them Global constraints such as Saoko Chiba Itakura and SDTW algorithm have also been applied to enhance retrieval efficiency Byintroducing the SDTW algorithm that behaves statistically with the sequences and considers eachfrequency sample as a Gaussian distribution around that sample the retrieval efficiency has beenenhanced Moreover dimensionality reduction approaches like FTW PDTW and IDDTW have beenapplied to reduce time and computational complexity By applying these approaches there will be atrade off between retrieval efficiency and time performance of the system These approaches usuallyutilize PAA coefficients in accompany to DTW algorithm for representation of reduced dimensionquery and melodies Furthermore a criterion named Mean Reciprocal Rank MRR has been utilizedto determine accuracy level of the retrieval These are the issues that have been evaluated and studiedin this thesis KeywordsQBH system Melody matching Time series alignment Dynamic Time Warping algorithm Saoko Chiba and Itakura constraints Dimensionality Reduction
استاد داور :
مهدي برنجكوب، محمدرضايزدچي
