Digital audio track set recognition system
View Patent ↗A system and method are provided for matching a track set from a digital audio recording to metadata relating to the recording. Track duration data is obtained for the track set, and the track duration data is rounded. A search is performed for matching records in a first database based on the rounded track duration data, each resulting matching record having an identifier. Track duration data is retrieved from a second database based on the identifiers associated with the matching records. If more than one matching record is found, the track duration data retrieved from the second database is compared to the track duration data obtained for the track set to find a best matching record of in the second database. Metadata contained in the best matching record of the second database is output.
1. A method for generating records for a database for a collection of audio recordings, the method comprising:
obtaining a first sequence of track durations for each recording in the collection of audio recordings;
generating a rounding entry for each value in the first sequence of track durations by rounding each value in the first sequence of track durations in a selected direction to a nearest integer multiple of a rounding factor when the value is not within a predetermined range of an integer multiple of the rounding factor;
generating a first rounding entry and a second rounding entry for each value in the first sequence of track durations when the value is within a predetermined range of an integer multiple of a rounding factor, the first rounding entry being the value rounded in the selected direction based on the rounding factor and the second rounding entry being the value rounded opposite the selected direction based on the rounding factor;
wherein the predetermined range is an integer division of the rounding factor; and
storing each rounding entry in a first database, wherein the first database stores a plurality of permutations of track duration sequences resulting from the values that have been rounded.
2. The method of claim 1 , further comprising:
rounding track duration data for a track set to form a second sequence of track durations;
comparing the second sequence of track durations to the plurality of permutations of track duration sequences stored in the first database to identify one or more matching sequences; and
retrieving information relating to the track set based at least in part on the one or more matching sequences.
3. The method according to claim 2 , further comprising:
obtaining the first sequence of track durations for each recording of the collection of audio recordings from a second database containing a record corresponding to each recording, each record including metadata relating to the recording.
4. The method according to claim 3 , further comprising:
comparing, for each matching sequence, the track duration data retrieved from the second database to the track duration data for the track set;
determining a closest matching sequence; and
determining if the closest matching sequence meets a match quality threshold.
5. The method according to claim 1 , wherein the predetermined range is plus or minus an equidistant division value between a rounding factor mid-point and a rounding factor boundary.
6. A computer-readable medium having stored thereon sequences of instructions, the sequences of instructions including instructions which when executed by a computer system causes the computer system to perform:
obtaining a first sequence of track durations for each recording in a collection of audio recordings;
generating a rounding entry for each value in the first sequence of track durations by rounding each value in the first sequence of track durations in a selected direction to a nearest integer multiple of a rounding factor when the value is not within a predetermined range of an integer multiple of the rounding factor;
generating a first rounding entry and a second rounding entry for each value in the sequence of track durations when the value is within a predetermined range of an integer multiple of a rounding factor, the first rounding entry being the value rounded in a selected direction based on the rounding factor and the second rounding entry being the value rounded opposite the selected direction based on the rounding factor;
wherein the predetermined range is an integer division of the rounding factor; and
storing each rounding entry in a first database, wherein the first database stores a plurality of permutations of track duration sequences resulting from the values that have been rounded.
7. The computer-readable medium of claim 6 , having stored thereon sequences of instructions for causing the computer system to perform:
rounding track duration data for a track set to form a second sequence of track durations;
comparing the second sequence of track durations to the plurality of permutations of track duration sequences stored in the first database to identify one or more matching sequences; and
retrieving information relating to the track set based at least in part on the one or more matching sequences.
8. The computer-readable medium of claim 7 , having stored thereon sequences of instructions for causing the computer system to perform:
obtaining the first sequence of track durations for each recording of the collection of audio recordings from a second database containing a record corresponding to each recording, each record including metadata relating to the recording.
9. The computer-readable medium of claim 8 , having stored thereon sequences of instructions for causing the computer system to perform:
comparing, for each matching sequence, the track duration data retrieved from the second database to the track duration data for the track set;
determining a closest matching sequence; and
determining if the closest matching sequence meets a match quality threshold.
10. The computer readable medium according to claim 6 , wherein the predetermined range is plus or minus an equidistant division value between a rounding factor mid-point and a rounding factor boundary.
11. A system for generating records for a database for a collection of audio recordings, the system comprising:
a track set server adapted to receive a first sequence of track durations for each recording in the collection of audio recordings and to generate a rounding entry for each value in the first sequence of track durations by rounding each value in the first sequence of track durations in a selected direction to a nearest integer multiple of a rounding factor when the value is not within a predetermined range of an integer multiple of the rounding factor;
the track set server further adapted to generate a first rounding entry and a second rounding entry for each value in the sequence of track durations when the value is within a predetermined range of an integer multiple of a rounding factor, the first rounding entry being the value rounded in a selected direction based on the rounding factor and the second rounding entry being the value rounded opposite the selected direction based on the rounding factor;
wherein the predetermined range is an integer division of the rounding factor; and
a first database adapted to store a plurality of permutations of track duration sequences resulting from the values that have been rounded.
12. The system according to claim 11 , wherein the track set server is further adapted to round track duration data for a track set to form a second sequence of track durations and to compare the second sequence of track durations to the plurality of permutations of track duration sequences stored in the first database to identify one or more matching sequences, and to retrieve information relating to the track set based at least in part on the one or more matching sequences.
13. The system according to claim 11 , further comprising:
a second database containing a record corresponding to each recording and adapted to store the first sequence of track durations for each recording of the collection of audio recordings, each record including metadata relating to the recording.
14. The system according to claim 13 , wherein the track set server is further adapted to compare, for each matching sequence, the track duration data retrieved from the second database to the track duration data for the track set;
determining a closest matching sequence; and
determining if the closest matching sequence meets a match quality threshold.
15. The system according to claim 11 , wherein the predetermined range is plus or minus an equidistant division value between a rounding factor mid-point and a rounding factor boundary.