Sound features extracting apparatus, sound data registering apparatus, sound data retrieving apparatus, and methods and programs for implementing the same
First Claim
1. A sound features extracting apparatus comprising:
- an audio signal input part which receives an audio signal of sound data;
a frequency analyzer which analyzes the frequency of each predetermined time frame of said audio signal received from said audio signal input part, and which outputs a signal of each frequency band;
an interframe variation calculator which calculates a degree of variation between two time frames in said signals of said frequency band received from said frequency analyzer by means of norm calculation; and
an average calculator which determines an average of said 1.5 interframe variations calculated by said interframe variation calculator over all the frames of said audio signal to be processed, wherein said sound features extracting apparatus calculates a degree of spectrum change which is one of primary features of said audio signal.
2 Assignments
0 Petitions
Accused Products
Abstract
The present invention implements a method and an apparatus for retrieving a sound data desired by the user on the basis of its subjective impression over the sound data. The subjective impression on the desired sound data is entered by the user and converted to a numerical value. A target sound impression value which is a numerical form of the impression on the sound data is calculated from the numerical value. The target sound impression value is then used as a retrieving key for accessing a sound database where the audio signal and the sound features of a plurality of the sound data are stored. This allows the desired sound data to be retrieved on the basis of the subjective impression of the user on the sound data.
56 Citations
28 Claims
-
1. A sound features extracting apparatus comprising:
-
an audio signal input part which receives an audio signal of sound data;
a frequency analyzer which analyzes the frequency of each predetermined time frame of said audio signal received from said audio signal input part, and which outputs a signal of each frequency band;
an interframe variation calculator which calculates a degree of variation between two time frames in said signals of said frequency band received from said frequency analyzer by means of norm calculation; and
an average calculator which determines an average of said 1.5 interframe variations calculated by said interframe variation calculator over all the frames of said audio signal to be processed, wherein said sound features extracting apparatus calculates a degree of spectrum change which is one of primary features of said audio signal.
-
-
2. A sound features extracting apparatus comprising:
-
an audio signal input part which receives an audio signal of sound data;
a frequency analyzer which analyzes the frequency of each predetermined time frame of said audio signal received from said audio signal input part, and which outputs a signal of each frequency band;
a rise component detector which calculates a rise component in said signal of each frequency band received from said the frequency analyzer; and
a rise frequency calculator which examines the presence of a rise component in said signal of each frequency band obtained from said rise component detector, which sums the rise components in each time frame, and which calculates an average of the sums in all the frames of said audio signal to determine the frequency of rises, wherein said sound features extracting apparatus calculates an average of sound emissions which is one of primary features of said audio signal.
-
-
3. A sound features extracting apparatus comprising:
-
an audio signal input part which receives a audio signal of sound data;
a first frequency analyzer which analyzes the frequency of each predetermined time frame of said audio signal received from said audio signal input part, and which outputs a signal of each frequency band;
a rise component calculator which detects a rise component in said signal of each frequency received from said first frequency analyzer, and which sums said rise components along the frequency base to determine rise component in each time frame;
an auto-correlation function calculator which calculates an auto-correlation function of said rise components;
a second frequency analyzer which analyzes frequency of said auto-correlation function calculated by said autocorrelation function calculator, and which outputs a signal of each frequency band;
a direct-current component detector which detects a direct-current component in said signal outputted from said second frequency analyzer;
a peak detector which detects signal of each frequency band which is maximum in the power from said signal outputted from said second frequency analyzer; and
a ratio calculator which divides the power of said output 20 of said direct-current component detector by the power of said output of said peak detector, wherein said sound features extracting apparatus calculates a non-periodic property of sound emission which is one of primary features of said audio signal.
-
-
4. A sound features extracting apparatus comprising:
-
an audio signal input part which receives an audio signal of sound data;
a frequency analyzer which analyzes the frequency of each predetermined time frame of said audio signal received from said audio signal input part, and which outputs a signal of each frequency band;
a rise component calculator which detects a rise component in said signal of each frequency received from said frequency analyzer, and which sums said rise components along the frequency base to determine rise component in each time frame;
an auto-correlation function calculator which calculates an auto-correlation function of the said components obtained from said rise component calculator;
a peak calculator which calculates a position and an amplitude of each peak in said signal outputted from said autocorrelation function calculator;
a tempo interval time candidate calculator which calculates some candidates for a tempo interval time of said sound data from said peaks of said auto-correlation function calculated by said peak calculator;
a cycle structure calculator which calculates a cycle structure of said sound data from said peaks of said autocorrelation function calculated by said peak calculator; and
a tempo interval time detector which determines a value of the most likely tempo interval time of said sound data from said candidates calculated by said tempo interval time candidate calculator with reference to said signal outputted from said rise component calculator and said signal outputted from said cycle structure calculator, wherein said sound features extracting apparatus calculates tempo interval time which is one of primary features of said audio signal. - View Dependent Claims (5, 6)
-
-
7. A sound features extracting apparatus comprising:
-
an audio signal input part which receives an audio signal of sound data;
a first frequency analyzer which analyzes the frequency of each predetermined time frame of said audio signal received from said audio signal input part, and which outputs a signal of each frequency band;
a rise component calculator which detects a rise component in said signal of each frequency received from said first frequency analyzer, and which sums said rise components along the frequency base to determine said rise component in each time frame;
an auto-correlation function calculator which calculates an auto-correlation function of said rise components outputted from said rise component calculator;
a first peak calculator which calculates a position and an amplitude of each peak in said signal outputted from said autocorrelation function calculator;
a tempo interval time candidate calculator which calculates some candidates for a tempo interval time of said sound data from said peaks of said auto-correlation function calculated by said first peak calculator;
a cycle structure calculator which calculates a cycle structure of said sound data from said peaks of the autocorrelation function calculated by said first peak calculator;
a tempo interval time detector which determines a value of the most likely tempo interval time of said sound data from said candidates calculated by said tempo interval time candidate calculator with reference to said signal outputted from said rise component calculator and said signal outputted from said cycle structure calculator;
a second frequency analyzer which analyzes frequency of said auto-correlation function and which outputs a signal of each frequency band;
a second peak detector which detects a signal of each frequency band which is maximum in the power from said signal outputted from said second frequency analyzer; and
a ratio calculator which calculates a ratio between said tempo interval time of said sound data outputted from said tempo interval time detector and said values outputted from said second peak detector, wherein said sound features extracting apparatus calculates a ratio of the tempo interval time which is one of primary features of the audio signal.
-
-
8. A sound features extracting apparatus comprising:
-
an audio signal input part which receives an audio signal of sound data;
a first frequency analyzer which analyzes the frequency of each predetermined time frame of said audio signal received from the audio signal input part, and which outputs a signal of each frequency band;
a rise component calculator which detects a rise component in said signal of each frequency received from said first frequency analyzer, and which sums said rise components along the frequency base to determine said rise component in each time frame;
an auto-correlation function calculator which calculates an auto-correlation function of said rise components outputted from said the rise component calculator;
a peak calculator which calculates a position and an amplitude of each peak in said signal outputted from said autocorrelation function calculator;
a tempo interval time candidate calculator which calculates some candidates for a tempo interval time of said sound data from said peaks of said auto-correlation function calculated by said peak calculator;
a cycle structure calculator which calculates a cycle structure of said sound data from said peaks of the autocorrelation function calculated by said peak calculator;
a tempo interval time detector which determines a value of the most likely tempo interval time of said sound data from said candidates calculated by said tempo interval time candidate calculator with reference to said signal outputted from said rise component calculator and said signal outputted from said cycle structure calculator;
a second frequency analyzer which analyzes frequency of said auto-correlation function, and to which outputs a signal of each frequency band;
a frequency calculator which calculates a frequency equal to said tempo interval time divided by an integer from said tempo interval time of said sound data outputted from said tempo interval time detector; and
a value reference part which refers the frequency output to said second frequency analyzer, and which outputs a value which represents the peak in proximity of the frequency outputted from said frequency calculator, wherein said sound features extracting apparatus calculates said value of a beat intensity which is one of primary features of said audio signal.
-
-
9. A sound features extracting apparatus comprising:
-
an audio signal input part which receives an audio signal of sound data;
a first frequency analyzer which analyzes the frequency of each predetermined time frame of said audio signal received from the audio signal input part, and which outputs a signal of each frequency band;
a rise component calculator which detects a rise component in said signal of each frequency received from said first frequency analyzer, and which sums said rise components along the frequency base to determine said rise component in each time frame;
an auto-correlation function calculator which calculates an auto-correlation function of said rise components outputted from said the rise component calculator;
a peak calculator which calculates a position and an amplitude of each peak in said signal outputted from said autocorrelation function calculator;
a tempo interval time candidate calculator which calculates some candidates for a tempo interval time of said sound data from said peaks of said auto-correlation function calculated by said peak calculator;
a cycle structure calculator which calculates a cycle structure of said sound data from said peaks of the autocorrelation function calculated by said peak calculator;
a tempo interval time detector which determines a value of the most likely tempo interval time of said sound data from said candidates calculated by said tempo interval time candidate calculator with reference to said signal outputted from said rise component calculator and said signal outputted from said cycle structure calculator;
a second frequency analyzer which analyzes frequency of said auto-correlation function, and to which outputs a signal of each frequency band;
a first frequency calculator which calculates a frequency equal to said tempo interval time divided by an integer from said tempo interval time of said sound data outputted from said tempo interval time detector;
a first value reference part which refers the frequency output of said second frequency analyzer, and which outputs a value which represents the peak in proximity of the frequency output of said first frequency calculator;
a second frequency calculator which calculates a frequency equal to {fraction (1/4)} of said tempo interval time from said tempo interval time of said sound data determined by said tempo interval time detector;
a second value reference part which refers the frequency output of said second frequency analyzer and which outputs a value which represents the peak in proximity of said frequency output of said second frequency calculator; and
a ratio calculator which calculates a ratio between said value output of said first value reference part and said value output of said second value reference part, wherein said sound features extracting apparatus calculates said ratio of beat intensity which is one of primary features of said audio signal.
-
-
10. A sound data registering apparatus for registering an audio signal of sound data, comprising:
-
an audio signal input part which receives said audio signal of said sound data;
a sound data feature extractor which extracts one of sound the features which include a spectrum variation, an average number of sound emission, a sound emission non-periodic property, a tempo interval time, a tempo interval time ratio, a beat intensity, and beat intensity ratio from said audio signal received by the audio signal input part; and
a sound impression values calculator which calculates a sound impression value which is a numerical form of the acoustic psychological impression of said sound data from said sound features, wherein said sound data registering apparatus registers said audio signal received by the audio signal input part, said sound features, and said sound impression values. - View Dependent Claims (11, 13, 15, 16, 17, 18, 19, 20)
-
-
12. A sound data retrieving apparatus for retrieving sound data from a sound database, comprising:
-
a retrieving query input part which outputs a numerical form of each sound data requirement given by an user;
a target sound impression values calculator which calculates a target sound impression value which is a numerical form of the acoustic psychological impression given from outputs of said retrieving query input part; and
a sound impression values retriever which accesses said sound database with said target sound impression values used as a retrieving key. - View Dependent Claims (14)
-
-
21. A method for extracting sound features for extracting the sound features from an audio signal of sound data, comprising the following steps of:
-
inputting said audio signal of said sound data; and
extracting one of sound features which include a spectrum variation, an average number of sound emission, a sound emission non-periodic property, a tempo interval time, a tempo interval time ratio, a beat intensity, and beat intensity ratio from said audio signal received by the audio signal inputting step.
-
-
22. A method for registering sound data for registering the audio signal of a sound data, comprising the following steps of:
-
inputting said audio signal of said sound data;
extracting one of sound features which include a spectrum variation, an average number of sound emission, a sound emission non-periodic property, a tempo interval time, a tempo interval time ratio, a beat intensity, and beat intensity ratio from said audio signal received by the audio signal inputting step; and
calculating a sound impression value which is a numerical form of the acoustic psychological impression from said sound features of the sound data, wherein the audio signal received at said audio signal inputting step is registered together with said sound features and said sound impression values. - View Dependent Claims (24, 28)
-
-
23. A method for retrieving sound data of retrieving a sound data from a sound database, comprising the following steps of:
-
inputting retrieving query of a required sound data given by an user and outputting it as a numerical form;
calculating a target sound impression values which is a numerical form of acoustic psychological impression given from an output of said retrieving query inputting step; and
accessing said sound database with said target sound impression values used as a retrieving key.
-
-
25. A program for extracting sound features for allowing a computer to have the functions of:
-
an audio signal input part which inputs said audio signal of said sound data; and
a sound data extractor which extracts one of sound features which include a spectrum variation, an average number of sound emission, a sound emission non-periodic property, a tempo interval time, a tempo interval time ratio, a beat intensity, and beat intensity ratio from said audio signal received by said audio signal input part.
-
-
26. A program for registering sound data for allowing a computer to have the functions of:
-
an audio signal input part which inputs said audio signal of said sound data;
a sound data extractor which extracts one of sound features which include a spectrum variation, an average number of sound emission, a sound emission non-periodic property, a tempo interval time, a tempo interval time ratio, a beat intensity, and beat intensity ratio from said audio signal received by said audio signal input part; and
a sound impression values calculator for calculating a sound impression value which is a numerical form of the acoustic psychological impression of the sound data from said sound features, wherein the audio signal received at said audio signal input part is registered together with said sound features and said sound impression values.
-
-
27. A program for retrieving sound data for allowing a computer to have the functions of:
-
a retrieving query input part which receives sound data requirement by the user and outputs a numerical form thereof;
a target sound impression data calculator which calculates a target sound impression value which is a numerical form of acoustic psychological impression given from an output of said retrieving query input part; and
a sound impression values retriever which accesses said sound database with said target sound impression value used as a retrieving key.
-
Specification