Method and apparatus for audio signal classification
First Claim
Patent Images
1. A method of audio classification comprising:
- determining, by a user equipment, a signal identification value for a downlink encoded audio signal received by the user equipment, wherein determining the signal identification value comprises identifying at least two frames as sample values of the encoded audio signal, low pass filtering the sample values of the encoded audio signal, determining a maximum root mean square value and a minimum root mean square value of the low pass filtered encoded audio signal sample values, and determining a ratio value of the maximum root mean square value and the minimum root mean square value of the low pass filtered encoded audio signal sample values based on the at least two frames, where the ratio value is used to determine the signal identification value;
determining, by the user equipment, at least one noise level value for the received downlink encoded audio signal, wherein determining the at least one noise level value comprises high pass filtering the sample values of the encoded audio signal, determining at least two root mean square values for the high pass filtered encoded audio signal sample values;
selecting a minimum root mean square value from the at least two root mean values; and
low pass filtering the minimum root mean square value from the at least two root mean values to determine the at least one noise level value for the downlink encoded audio signal;
comparing, by the user equipment, the signal identification value against a signal identification threshold, and the at least one noise level value against an associated noise level threshold; and
identifying, by the user equipment, the received downlink encoded audio signal as a speech audio signal or a music audio signal dependent on the comparison.
8 Assignments
0 Petitions
Accused Products
Abstract
An apparatus comprising at least one processor and at least one memory including computer program code the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform determining a signal identification value for an audio signal, determining at least one noise level value for the audio signal, comparing the signal identification value against a signal identification threshold and each of the at least one noise level value against an associated noise level threshold, and identifying the audio signal dependent on the comparison.
59 Citations
17 Claims
-
1. A method of audio classification comprising:
-
determining, by a user equipment, a signal identification value for a downlink encoded audio signal received by the user equipment, wherein determining the signal identification value comprises identifying at least two frames as sample values of the encoded audio signal, low pass filtering the sample values of the encoded audio signal, determining a maximum root mean square value and a minimum root mean square value of the low pass filtered encoded audio signal sample values, and determining a ratio value of the maximum root mean square value and the minimum root mean square value of the low pass filtered encoded audio signal sample values based on the at least two frames, where the ratio value is used to determine the signal identification value; determining, by the user equipment, at least one noise level value for the received downlink encoded audio signal, wherein determining the at least one noise level value comprises high pass filtering the sample values of the encoded audio signal, determining at least two root mean square values for the high pass filtered encoded audio signal sample values;
selecting a minimum root mean square value from the at least two root mean values; and
low pass filtering the minimum root mean square value from the at least two root mean values to determine the at least one noise level value for the downlink encoded audio signal;comparing, by the user equipment, the signal identification value against a signal identification threshold, and the at least one noise level value against an associated noise level threshold; and identifying, by the user equipment, the received downlink encoded audio signal as a speech audio signal or a music audio signal dependent on the comparison. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to:
-
determine a signal identification value for a downlink encoded audio signal received by the apparatus, wherein determining the signal identification value comprises identifying at least two frames as sample values for the encoded audio signal, low pass filtering the sample values of the encoded audio signal, determining a maximum root mean square value and a minimum root mean square value of the low pass filtered encoded audio signal sample values, and determining a ratio value of the maximum root mean square value and the minimum root mean square value of the low pass filtered encoded audio signal sample values based on the at least two frames, where the ratio value is used to determine the signal identification value; determine at least one noise level value for the received downlink encoded audio signal, wherein determining the at least one noise level value comprises high pass filtering the sample values of the encoded audio signal, determining at least two root mean square values for the high pass filtered encoded audio signal sample values;
selecting a minimum root mean square value from the at least two root mean values; and
low pass filtering the minimum root mean square value from the at least two root mean values to determine the at least one noise level value for the downlink encoded audio signal;compare the signal identification value against a signal identification threshold, and the at least one noise level value against an associated noise level threshold; and identify the received downlink encoded audio signal as a speech audio signal or a music audio signal dependent on the comparison. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17)
-
Specification