2007 multimedia system final paper presentation music recognition 492410021 蘇冠年 492410070...

29
2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇蘇蘇 492410070 蘇蘇蘇

Upload: mavis-bell

Post on 11-Jan-2016

240 views

Category:

Documents


3 download

TRANSCRIPT

Page 1: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

2007 Multimedia System Final Paper Presentation

Music Recognition 492410021 蘇冠年

492410070 蔡尚穎

Page 2: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Introduction

• In future, the problem is not anymore how to get access to multimedia content, the task is how to find what I’m looking for…

Page 3: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Music Recognition System

Training

Data Base

Recognition

Result

Input Data

Page 4: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Before the Algorithm

• Practical Problems

- Disturbance of noise

- Disturbance of Harmonic

- Singer and instrument

- …

Page 5: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Algorithm I

• Pitch detection - notes, chords …

• Based on frequency domain

- according to music characteristics, it analyzed spectrum at the music pitches

- using Wavelet Transform and DTFT (Discrete-Time Fourier Transform)

Page 6: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Frequency Analysis

• Music signal is of typical time-frequency distribution

and has short-time steady property

Page 7: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Frequency Analysis

• Wavelet Transform

- Daub4 Wavelet base by Mallet Algorithm

• DTFT to calculate amplitude

- pitch frequency as parameter ω

Page 8: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Frequency Analysis

• Analyzed result

Page 9: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Notes Recognition

• Step 1: Note Voting - 1. analyzed each data by wavelet transform in frequency domain.

- 2. picked out a numbers of notes that have biggest amplitudes in a data as candidate notes.

- 3. count of the appearance times of the candidate notes in several neighbor dada

• Step 2 : denote the different segments of the music

• Step 3 : selected the note that appears most and has the biggest average amplitude

Page 10: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

- A piece of music

- Wave form of the data

Page 11: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

- the spectrogram of segment 1

Page 12: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

- determine the note

Page 13: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Chords Recognition

• What is the chord ?

• The chord components always have the similar amplitude in frequency domain

Page 14: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Chords Recognition

• Step 1 : define as a set of candidate notes

and as the amplitude of the notes p

• Step 2 : calculate likelihood coefficient of each note

• Step 3 : coefficient L is the average likelihood coefficient among the notes in a candidate chord

Page 15: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

- A piece of music

- Wave form of the data

Page 16: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

- the spectrogram of segment 1

Page 17: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

- determine the chords

Page 18: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Algorithm II

• Items of recognizing

• Single-pitched melody

• Multiple-instrument melody

Page 19: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎
Page 20: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Pre-Processing

Page 21: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Adaptive Template-matching

• Phase Tracking

• Template Filtering

Page 22: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Phase Tracking

z : input signal

r , i : possible sound

p : narrow-band filter

Page 23: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Phase Tracking

• fs : sampling frequency

• fc : center frequency of the band-pass filter

Page 24: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Template Filtering

• minimization of J

z(k) : input sum of template waveforms

hn(m) : convolution of the filter coefficients

rn(k) : phase-adjusted waveform

Page 25: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Template Filtering

Page 26: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Music Stream Networks

• Problem of local information

• Bayesian probabilistic network

Page 27: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎
Page 28: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Conclusion

Page 29: 2007 Multimedia System Final Paper Presentation Music Recognition 492410021 蘇冠年 492410070 蔡尚穎

Reference

1. Zheng Cao, Shengxiao Guan, Zengfu Wang. “A Real-time Algorithm for Music Recognition Based on Wavelet Transform” IEEE June 21 - 23, 2006, Dalian, China

2. Kunio Kashino ,Hiroshi Murase . “Music Recognition using Note Transition Context”

IEEE 1998, NTT Basic Research Laboratories

3. Karlheinz Brandenburg. “Digital Entertainment: Media technologies for the future”

IEEE 2006 , Fraunhofer IDMT & Technische Universität Ilmenau

4. Chen Genfand, Xia Shunren. “The study and prototype system of printed music recognition”. IEEE 2003

5. D Bainbridge , T C Bell. “Dealing with superimposed objects in optical music recognition” IEEE 15-17 July 1997 Universities of Waikato and Canterbury, New Zealand

6. MALLAT'S FAST WAVELET ALGORITHM: RECURSIVE COMPUTATION OF

CONTINUOUS-TIME WAVELET COEFFICIENTS