Multi-feature speech/music discrimination system2010-03-29 00:00:00types of classifiers for labeling test
points on the basis of the feature data are disclosed. A preferred set of classifiers is based upon variations of a nearest-neighbor approach, including a K-d tree spatial partitioning technique.Claims
What is claimed is:
1. A method for discriminating between speech and music content in an audio signal, comprising the steps of:
selecting a set of audio signal samples;
measuring values for a plurality of features in each sample of said set of samples;
defining a multi-dimensional feature space containing data
points which respectively correspond to the measured feature values for each sample, and labelling each data point as relating to speech or music;
measuring feature values for a test sample of an audio signal and determining a corresponding data point in said feature space;
determining the label for at least one data point in said feature space which is close to the data point corresponding to said test sample; and
classifying the test sample in accordance with the determined label.
2. The method of claim 1 wherein said determining step comprises determining the label for the data point in said feature space which is nearest to the data point for said test sample.
3. The method of claim 1 wherein said determining step comprises the steps of identifying a plurality of data
points which are nearest to the data point for said test sample, and selecting the label which is associated with a majority of the identified data
points.
4. The method of claim 1 wherein said determining step comprises the steps of dividing the feature space into regions in accordance with said features, labelling each region as relating to speech data or music data in accordance with the labels for the data
points in the region, and determining the region in said feature space in which the data point for said test sample is located.
5. The method of claim 1 wherein one of said features is the variation of spectral flux among a series of frames of the audio signal.
6. The method of claim 1 wherein one of said features is a pulse metric which identifies correspondence of modulation frequency peaks in different respective frequency bands of the audio signal.
7. The method of claim 1 wherein one of said features is measured by the steps of determining the mean power for a series of frames of said audio signal, and determining the proportion of frames in said series whose power is less than a predetermined fraction of said mean power.
8. The method of claim 1 wherein one of said features is the proportion of energy in the audio signal having speech modulation frequencies.
9. The method of claim 8 wherein said speech modulation frequencies are around 4 Hz.
10. The method of claim 1 wherein said audio signal is divided into a sequence of frames, and wherein values for some of said features are measured for individual frames, and values for others of said features relate to variations of measured values over a series of frames.
11. The method of claim 1 wherein said audio signal is divided into a sequence of frames and further including the steps of classifying each frame of the test sample as relating to speech or music, examining the classifications for a plurality of successive frames, and determining a final classification on the basis of the examined classifications.
12. A method for determining whether an audio signal contains music content, comprising the steps of:
dividing the audio signal into a plurality of frequency bands;
determining modulation frequencies of the audio signal in each band;
identifying the amount of correspondence of the modulation frequencies among the frequency bands; and
classifying whether audio signal has musical content in dependence upon the identified amount of correspondence;
wherein the step of determining the modulation frequencies in a frequency band comprises the steps of:
determining an energy envelope of the frequency band;
identifying peaks in the energy envelope; and
calculating a windowed autocorrelation of the peaks.
13. A method for determining whether an audio signal contains music content, comprising the steps of:
dividing the audio signal into a plurality of frequency bands;
determining modulation frequencies of the audio signal in each band;
identifying the amount of correspondence of the modulation frequencies among the frequency bands; and
classifying wheth...
Transducer for stringer musical instrument2010-03-01 00:00:00issued to S. E. Lover on July 28, 1959.
Prior hum elimination expedients, while effective in reducing 60 cycle hum, have disadvantages which limit their overall effectiveness. A conventional side-by-side arrangement of coils senses vibrations of each string at two relatively widelyspaced
points along the string, causing cancellation of certain frequencies other than the 60 cycle hum frequency and consequent degradation of musical quality. With coils mounted one on top of the other, the musical signal is not so degraded but theoutput signal is relatively weak.
U.S. Pat. No. 3,711,619 which issued to Jones et al on Jan. 16, 1973 discloses a pick-up device involving multiple coils in which the fidelity of sound reproduced is stated as being substantially improved over other conventional pick-updevices. In this patent, the number of turns constituting one winding are substantially different from the number of turns constituting another winding. A turns ratio of 4:1 is disclosed. The patentee discloses forming two different windings of thesame size wire, although brie...
Generation of noise-like tones in an electronic musical instrument2010-02-27 00:00:00of
points defining the waveform of a musical tone are transferred to a digital-to-analog converter at a rate proportional to the pitch of the tone being generated. Noise is superimposed on the musical tone by means of a random binary signal generator which controls a circuit for modifying selected ones of the digital values as they are transferred from the master data list to the converter. Modification of the selected values may be by a right shift operation, a 2's complement operation, or by selective delay.ClaimsWhat is claimed is:
1. An electronic tone synthesizer for generating an audio signal having a predetermined waveform in which noise is superimposed on the audio signal, comprising: a group ofdigital words representing the relative amplitudes of equally spaced
points defining the waveform of an audio signal, a digital-to-analog converter, means transferring the digital words sequentially from the generating means and applying the words inrepetitive sequence to the converter, the transferring means including means for modifying the digital value of any selected word as it is being transferred, a random signal generator for generating an output signal at random time intervals, and meansresponsive to the random output signal for momentarily activating said means for modifying a word being transferred, whereby the digital words are modified at random during transfer.
2. Apparatus of claim 1 wherein said means for modifying said digital values includes a right shift circuit for shifting the digital values of the randomly selected words numerically at least one place to the right.
3. Apparatus of claim 1 wherein said means for modifying said digital values includes a 2's complement circuit for generating the 2's complement of the digital values of the randomly selected words.
4. Apparatus of claim 1 wherein said means for modifying said digital values includes means for delaying the time of transfer at which a selected word is transferred from the generating means.
5. Apparatus of claim 2 wherein the transferring means further includes a shift register, a right shift circuit for transferring each of the digital words in sequence from the generating means to ...
