System And Method For Identifying Original Music
We disclose useful components of a method and system that allow identification of music from the song or sound using only the sound of the audio being played. A system built using the method and device components disclosed processes inputs sent from a mobile phone over a telephone or data connection, though inputs might be sent through any variety of computers, communications equipment, or consumer audio devices over any of their associated audio or data networks.
1 . A method of recognizing music, including:
receiving audio at a phone or other mobile device;
processing the sound in chunks and forwarding results of the processing to a server as the chunks are processed;
causing the server to initiate recognition of the chunks beginning with two seconds of the chunks or less;
receiving back from the server at least one identifier of a matched song upon a successfully matched sequence of chunks.
2 . The method of claim 1 , further including receiving back from the server an alignment value that indicates an alignment of at least one of the chunks relative to a beginning of the matched song.
3 . The method of claim 1 , further including processing chunks with a plurality of starting points for a first chunk that are offset by fractions of a length of the chunk.
4 . The method of claim 3 , wherein a second starting point is offset from a first starting point by about 25 percent of the length of the chunk.
5 . The method of claim 3 , wherein a hop length between chunks processed is about 50 percent of the length of the chunk.
6 . A device that captures audio and reports matches to audio samples, at least one processor configured to carry out actions including:
receiving audio at a phone or other mobile device;
processing the sound in chunks and forwarding results of the processing to a server as the chunks are processed;
causing the server to initiate recognition of the chunks beginning with two seconds of the chunks or less;
receiving back from the server at least one identifier of a matched song upon a successfully matched sequence of chunks.
7 . The device of claim 6 , wherein the processor further configured to carry out actions including receiving back from the server an alignment value that indicates an alignment of at least one of the chunks relative to a beginning of the matched song.
8 . The device of claim 6 , wherein the processor further configured to carry out actions including processing chunks with a plurality of starting points for a first chunk that are offset by fractions of a length of the chunk.
9 . The device of claim 8 , wherein a second starting point is offset from a first starting point by about 25 percent of the length of the chunk.
10 . The device of claim 8 , wherein a hop length between chunks processed is about 50 percent of the length of the chunk.
11 . A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by at least one processor cause the processor to perform operations including:
receiving audio at a phone or other mobile device;
processing the sound in chunks and forwarding results of the processing to a server as the chunks are processed;
causing the server to initiate recognition of the chunks beginning with two seconds of the chunks or less;
receiving back from the server at least one identifier of a matched song upon a successfully matched sequence of chunks.
12 . The non-transitory computer storage medium of claim 11 , wherein the instructions further cause the processor to perform actions including receiving back from the server an alignment value that indicates an alignment of at least one of the chunks relative to a beginning of the matched song.
13 . The non-transitory computer storage medium of claim 11 , wherein the instructions further cause the processor to perform actions processing chunks with a plurality of starting points for a first chunk that are offset by fractions of a length of the chunk.
14 . The non-transitory computer storage medium of claim 13 , wherein a second starting point is offset from a first starting point by about 25 percent of the length of the chunk.
15 . The non-transitory computer storage medium of claim 13 , wherein a hop length between chunks processed is about 50 percent of the length of the chunk.