2016/6/41 Recent Improvement Over QBSH and AFP J.-S. Roger Jang (張智星) Multimedia Information Retrieval (MIR) Lab CSIE Dept, National Taiwan Univ.

Slides:



Advertisements
Similar presentations
Introduction to Information Retrieval Introduction to Information Retrieval Lecture 7: Scoring and results assembly.
Advertisements

Database management system (DBMS)  a DBMS allows users and other software to store and retrieve data in a structured way  controls the organization,
Feature Selection for Pattern Recognition J.-S. Roger Jang ( 張智星 ) CSIE Dept., National Taiwan University ( 台灣大學 資訊工程系 )
Dynamic Time Warping (DTW)
Pete Bohman Adam Kunk.  Introduction  Related Work  System Overview  Indexing Scheme  Ranking  Evaluation  Conclusion.
Standard Template Library Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
Shallow Copy Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
Onset Detection in Audio Music J.-S Roger Jang ( 張智星 ) MIR LabMIR Lab, CSIE Dept. National Taiwan University.
Retrieval Methods for QBSH (Query By Singing/Humming) J.-S. Roger Jang ( 張智星 ) Multimedia Information Retrieval.
Performance Evaluation: Estimation of Recognition rates J.-S. Roger Jang ( 張智星 ) CSIE Dept., National Taiwan Univ.
PCA & LDA for Face Recognition
NM7613: Music Signal Analysis and Retrieval 音樂訊號分析與檢索 Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
Principal Component Analysis (PCA)
2015/9/131 Stress Detection J.-S. Roger Jang ( 張智星 ) MIR LabMIR Lab, CSIE Dept., National Taiwan Univ.
Endpoint Detection ( 端點偵測 ) Jyh-Shing Roger Jang ( 張智星 ) MIR Lab, CSIE Dept National Taiwan Univ., Taiwan.
CSIE Dept., National Taiwan Univ., Taiwan
National Taiwan University
HPCLatAm 2013 HPCLatAm 2013 Permutation Index and GPU to Solve efficiently Many Queries AUTORES  Mariela Lopresti  Natalia Miranda  Fabiana Piccoli.
2015/10/221 Progressive Filtering and Its Application for Query-by-Singing/Humming J.-S. Roger Jang ( 張智星 ) Multimedia Information Retrieval Lab CS Dept.,
加速以 GPU 為運算核心的二階段哼唱選歌 系統 A CCELERATING A T WO -S TAGE Q UERY BY S INGING /H UMMING S YSTEM U SING GPU S Student:Andy Chuang ( 莊詠翔 )
Demos for QBSH J.-S. Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
Singly Linked Lists Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University 1.
Sorting Algorithms Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
RuSSIR 2013 QBSH and AFP as Two Successful Paradigms of Music Information Retrieval Jyh-Shing Roger Jang ( 張智星 ) MIR Lab, CSIE Dept.
Sparse Vectors & Matrices Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
Binary Search Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
Music Information Retrieval: Overview and Challenges
QBSH Corpus The QBSH corpus provided by Roger Jang [1] consists of recordings of children’s songs from students taking the course “Audio Signal Processing.
Audio Fingerprinting as a New Task for MIREX-2014 Chung-Che Wang Jyh-Shing Roger Jang.
ACCELERATING QUERY-BY-HUMMING ON GPU Pascal Ferraro, Pierre Hanna, Laurent Imbert, Thomas Izard ISMIR 2009 Presenter: Chung-Che Wang (Focus on the performance.
Sudhanshu Khemka.  Treats each document as a vector with one component corresponding to each term in the dictionary  Weight of a component is calculated.
Content-Based MP3 Information Retrieval Chueh-Chih Liu Department of Accounting Information Systems Chihlee Institute of Technology 2005/06/16.
STL: Maps Jyh-Shing Roger Jang ( 張智星 ) CSIE Dept, National Taiwan University.
Some Research Activities in MIR Lab J.-S. Roger Jang ( 張智星 ) Multimedia Information Retrieval Lab CS.
Distance/Similarity Functions for Pattern Recognition J.-S. Roger Jang ( 張智星 ) CS Dept., Tsing Hua Univ., Taiwan
Discussions on Audio Melody Extraction (AME) J.-S. Roger Jang ( 張智星 ) MIR Lab, CSIE Dept. National Taiwan University.
Simulation of Stock Trading J.-S. Roger Jang ( 張智星 ) MIR Lab, CSIE Dept. National Taiwan University.
Linear Classifiers (LC) J.-S. Roger Jang ( 張智星 ) MIR Lab, CSIE Dept. National Taiwan University.
Final Project: English Preposition Usage Checker J.-S. Roger Jang ( 張智星 ) MIR Lab, CSIE Dept. National Taiwan University.
Introduction to Music Information Retrieval (MIR)
From C to C++ Jyh-Shing Roger Jang (張智星)
Introduction to ISMIR/MIREX
Onset Detection, Tempo Estimation, and Beat Tracking
Search in Google's N-grams
Quadratic Classifiers (QC)
MIR Lab: R&D Foci and Demos ( MIR實驗室:研發重點及展示)
DP for Optimum Strategies in Games
Query by Singing/Humming via Dynamic Programming
Large-Scale Content-Based Audio Retrieval from Text Queries
Introduction to Pattern Recognition
Distance and Midpoint Formulas
自我介紹 學歷: 研究方向: 經歷: 1984:學士,台大電機系 1992:博士,加州大學柏克萊分校、電機電腦系
Closing Remarks on MSAR-2017
ML for FinTech: Some Examples
Introduction to Music Information Retrieval (MIR)
Search in OOXX Games J.-S. Roger Jang (張智星) MIR Lab, CSIE Dept.
Introduction to Music Information Retrieval (MIR)
Circularly Linked Lists and List Reversal
Queues Jyh-Shing Roger Jang (張智星)
National Taiwan University
Query by Singing/Humming via Dynamic Programming
Insertion Sort Jyh-Shing Roger Jang (張智星)
Examples of Time Complexity
Scientific Computing: Closing 科學計算:結語
Selection Algorithm Jyh-Shing Roger Jang (張智星)
Naive Bayes Classifiers (NBC)
Game Trees and Minimax Algorithm
Duration & Pitch Modification via WSOLA
Sorting Algorithms Jyh-Shing Roger Jang (張智星)
Pre and Post-Processing for Pitch Tracking
Presentation transcript:

2016/6/41 Recent Improvement Over QBSH and AFP J.-S. Roger Jang (張智星) Multimedia Information Retrieval (MIR) Lab CSIE Dept, National Taiwan Univ.

-2- Outline zImprovement over QBSH (query by singing/huming) yWeights of rests and sorted error vectors yGPU optimization zImprovement over AFP (audio fingerprinting) yRe-ranking via learning to rank zNew tasks in MIREX yAFP ySinging/humming transcription

-3- Basic Method in QBSH zLinear scaling (LS)

-4- How To Deal with Rests in LS? zTo deal with rests (zero pitch) yReplace the rest with previous non-zero pitch zThis could go wrong for unstable trailing pitch due to yWrong endpoints yGlissando yVibrato

-5- Weights for Zero-pitch zAssign different weights for rests in the database and queries

-6- Example of Zero-pitch Weights

-7- Sorted Error Vector zCompute distance based on a partial set of growing errors, to deal with the problems of yDouble/half pitch error yMoving average

-8- QBSH Corpus Corpus 1Corpus 2Corpus 3 NameIndian (Indian)MIR-QBSHCHT (Chinese) Database formatwavemidi Database size Query set size 269 (chopped from 35 wave files) Query set format Pitch vector Query length10 sec8 sec sec

-9- Search Zero-pitch Weights zOptimize the weights for MIR-QBSH The best accuracy occurs at w1=0 and w2=2.

-10- Performance Evaluation Both SEV & zero-pitch weights improve top-10 accuracy!

-11- Efficiency Boost via GPU zWe can cut down QBSH response time via GPU (from 1.8 sec to 1.2 sec) by careful arrangement of blocks/threads and memory usage in order to ySpeed up memory access yAvoid bank conflicts zDetails of speedup via GPUsDetails of speedup via GPUs zDemo: toyshttp://mirlab.org/demo/miracletoys

-12- Improvement on AFP zRe-ranking of AFP by learning to rankRe-ranking of AFP by learning to rank zDemo:

-13- New Tasks in MIREX zWe’d like to propose two new tasks for MIREX yAudio fingerprintingAudio fingerprinting ySinging/humming transcriptionSinging/humming transcription

-14- Thank you for your attention! Questions & comments?