Download presentation
Presentation is loading. Please wait.
1
Sound Applications Advanced Multimedia Tamara Berg
2
Reminder HW2 due March 13, 11:59pm Questions?
3
Howard Leung
4
Audio Indexing and Retrieval Features for representing audio: – Metadata – low level features – high level audio features Example usage cases: Audio classification Music retrieval
5
Content Based Music Retrieval Extract music descriptions from a database of music documents. Extract music description from a query music document. Compute similarity between query and database descriptions. Retrieve similar music documents to query. Casey et al IEEE 2008
6
MIR tasks H: high level specificity – match specific instances of audio content. M: mid-level specificity – match high level audio features like melody, but do not match audio content. L: low specificity – match global (statistical) properties of the query Different usage cases require different descriptions and matching schema. Casey et al IEEE 2008
7
Metadata Most common method of accessing music Can be rich and expressive When catalogues become very large, difficult to maintain consistent metadata Useful for low specificity queries Casey et al IEEE 2008
8
Metadata Pandora.com – Uses metadata to estimate artist similarity and track similarity and creates personalized radio stations. Experts entered metadata of musical- cultural properties (20-30 minutes per track of an expert’s time – 50 person-years for 1 million tracks). Pandora.com Crowd sourced metadata repositories (gracenote, musicbrainz). Factual metadata (artist, album, year, title, duration). Cultural metadata (mood, emotion, genre, style).gracenote musicbrainz Automatic metadata methods – generate descriptions from community metadata automatically. Language analysis to associate noun and verb phrases with musical features (Whitman & Rifkin). Casey et al IEEE 2008
9
Content features Low level or high level Want features to be robust to certain changes in the audio signal – Noise – Volume – Sampling High level features will be more robust to changes, low level features will be less robust. Low level features will be easy to compute, high level difficult
10
Content features Low level or high level Want features to be robust to certain changes in the audio signal – Noise – Volume – Sampling High level features will be more robust to changes, low level features will be less robust. Low level features will be easy to compute, high level difficult
11
Content features Low level or high level Want features to be robust to certain changes in the audio signal – Noise – Volume – Sampling High level features will be more robust to changes, low level features will be less robust. Low level features will be easy to compute, high level difficult
12
Low level audio features Low level measurements of audio signal that contain information about a musical work. Can be computed periodically (10-1000 ms intervals) or beat synchronous. Casey et al IEEE 2008 In text analysis we had words, here we have to come up with our own set of features to compute from audio signal!
13
Example Low-Level Audio Features Howard Leung
15
Average number of times signal crosses zero amplitude value.
16
Howard Leung Average number of times signal crosses zero amplitude value.
17
Howard Leung Average number of times signal crosses zero amplitude value. 1 if true O o.w.
18
Howard Leung
19
Example Low-Level Audio Features Howard Leung
20
Frequency Domain Reminder How much of each describes the frequency spectrum of a signal. Li & Drew Signals can be decomposed into a weighted sum of sinusoids
21
Frequency domain features How do we get to frequency domain? TimeFrequency
22
DFT Discrete Fourier Transform (DFT) of the audio Converts to a frequency representation DFT analysis occurs in terms of number of equally spaced ‘bins’ Each bin represents a particular frequency range DFT analysis gives the amount of energy in the audio signal that is present within the frequency range for each bin Inverse Discrete Fourier Transform (IDFT) Converts from frequency representation back to audio signal.
23
DFT Discrete Fourier Transform (DFT) of the audio Converts to a frequency representation DFT analysis occurs in terms of number of equally spaced ‘bins’ Each bin represents a particular frequency range DFT analysis gives the amount of energy in the audio signal that is present within the frequency range for each bin Inverse Discrete Fourier Transform (IDFT) Converts from frequency representation back to audio signal.
24
DFT Discrete Fourier Transform (DFT) of the audio Converts to a frequency representation DFT analysis occurs in terms of number of equally spaced ‘bins’ Each bin represents a particular frequency range DFT analysis gives the amount of energy in the audio signal that is present within the frequency range for each bin Inverse Discrete Fourier Transform (IDFT) Converts from frequency representation back to audio signal.
25
Howard Leung
26
Filtering Removes frequency components from some part of the spectrum Low pass filter – removes high frequency components from input and leaves only low in the output signal. High pass filter – removes low frequency components from input and leaves only high in the output signal. Band pass filter – removes some part of the frequency spectrum.
27
How could you do this using the FT and IFT? Compute FT spectrum of input. Zero out the part of the frequency spectrum that you want to filter out. Compute the IFT of this modified spectrum -> output will be input with some frequency components removed.
28
How could you do this using the FT and IFT? f = input
29
How could you do this using the FT and IFT? f = input FT(f)
30
How could you do this using the FT and IFT? 1 0.* f = input FT(f)
31
How could you do this using the FT and IFT? 1 0.* f = input FT(f) Zero out some freq components
32
How could you do this using the FT and IFT? 1 0.* = f = input FT(f) Zero out some freq components x xxx xxxxx xxxx x
33
How could you do this using the FT and IFT? 1 0.* = f = input FT(f) Zero out some freq components IFT o = Frequency limited output x xxx xxxxx xxxx x
34
How could you do this using the FT and IFT? 1 0.* = f = input FT(f) Zero out some freq components IFT o = Frequency limited output x xxx xxxxx xxxx x What kind of filter is this?
35
How could you do this using the FT and IFT? f = input
36
How could you do this using the FT and IFT? f = input FT(f)
37
How could you do this using the FT and IFT? 1 0.* f = input FT(f)
38
How could you do this using the FT and IFT? 1 0.* f = input FT(f) Zero out some freq components
39
How could you do this using the FT and IFT? 1 0.* = f = input FT(f) Zero out some freq components x x x x xx xxxxxx x
40
How could you do this using the FT and IFT? 1 0.* = f = input FT(f) Zero out some freq components IFT o = Frequency limited output x x x x xx xxxxxx x
41
How could you do this using the FT and IFT? 1 0.* = f = input FT(f) Zero out some freq components IFT o = Frequency limited output x x x x xx xxxxxx x What kind of filter is this?
42
Howard Leung
44
Frequency Domain Reminder How much of each describes the frequency spectrum of a signal. Li & Drew Signals can be decomposed into a weighted sum of sinusoids
45
Pitch-Class Profile (PCP) Represent the energy due to each pitch class Integrates the energy in all octaves into a single band There are 12 equally spaced pitch classes in western tonal music. So, typically 12 bands in the PCP.
46
Pitch-Class Profile (PCP) Represent the energy due to each pitch class Integrates the energy in all octaves into a single band There are 12 equally spaced pitch classes in western tonal music. So, typically 12 bands in the PCP. How might we calculate this using the DFT?
47
High level music features High level intuitive information about a piece of music (melody, harmony etc). “It is melody that enables us to distinguish one work from another. It is melody that human beings are innately able to reproduce by singing, humming, and whistling. It is melody that makes music memorable: we are likely to recall a tune long after we have forgotten its text.” -Selfridge-Field Intuitive features, but hard to extract and ongoing areas of research. Casey et al IEEE 2008
48
Melody & Bass Estimation Melody and bass lines represented as continuous temporal trajectory of fundamental frequency, F0, (a series of musical notes). PreFEst ( Goto 1999 ) – Estimate the F0 trajectory in mid-high freq range of input -> melody. – Estimate the F0 trajectory in low freq range-> bass. Casey et al IEEE 2008
49
Chord Recognition Recognize chord progressions based on: - Estimated PCPs - Statistics of transitions between PCPs Casey et al IEEE 2008
50
Chord Recognition
52
Music as vector of features Once again we represent (music) documents as a vector of numbers – Each entry (or set of entries) in this vector is a different feature
53
Music as vector of features Once again we represent (music) documents as a vector of numbers – Each entry (or set of entries) in this vector is a different feature To retrieve music documents given a query we can: – Find exact matches – Find nearest match – Find nearby matches – Train a classifier to recognize a given category (genre, style etc).
54
Audio Similarity We have a description of a music document based on some set of features, now how do we compare two descriptions? Casey et al IEEE 2008
55
Usage examples
56
Howard Leung
63
Query by humming Requires robustness to variation because matches will not be exact Extract melody from dataset of songs Extract melody from hum Match by comparing similarities of melodies (nearby matches)
64
Copyright monitoring Compute fingerprints from database examples Compute fingerprint from query example Find exact matches
65
Best performing systems on MIREX 2007 Casey et al IEEE 2008
66
Music Browsing Musicream – UI for discovering and managing musical pieces. User can select a disc and listen to it. By dragging a disc in the flow, the user can easily pick out other similar pieces (attach similar discs). This interaction allows a user to unexpectedly come across various pieces similar to other pieces the user likes. Link to demo Casey et al IEEE 2008
67
Music Browsing Musicrainbow – UI for discovering unknown artists. Artists are mapped on a circular rainbow where colors represent different styles of music. Similar artists are mapped near each other. User rotates rainbow by turning a knob. Link to demo Casey et al IEEE 2008
68
Howard Leung
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.