Extracting Audio Fingerprints in the Compressed Domain
AssigneeGoogle Inc.
InventorsGiovanni Motta, Yang Lu
Life of this patent
Estimating the term…
Abstract
A computer-implemented method performed by a data processing apparatus includes receiving an audio signal that includes a frequency-domain representation of an audio file, extracting, from the audio signal, a plurality of frequency-domain data values that correspond to at least a portion of the audio file, compressing the plurality of data values to form a compressed frequency domain value file, and transmitting the compressed frequency domain value file to a server to identify the audio file.
Claims18
A computer-implemented method performed by a data processing apparatus, the method comprising:
- receiving an audio signal that includes a frequency-domain representation of an audio file;
- extracting, from the audio signal, a plurality of frequency-domain data values that correspond to at least a portion of the audio file;
- compressing the plurality of data values to form a compressed frequency domain value file;
- and
- transmitting the compressed frequency domain value file to a server to identify the audio file.
A computer-implemented method, comprising:
- performing a wavelet transformation on a compressed frequency domain value file of an audio file to convert the compressed frequency domain value file to a wavelet-vector;
- performing a Min-Hash operation on the wavelet-vector to create compressed frequency domain value representations of the audio file;
- and
- performing Locality Sensitive-Hashing (LSH) on the compressed frequency domain value representations to select compressed frequency domain value representations to comprise an audio fingerprint of the audio file.
A decoder, comprising:
- an input module that receives an audio signal including a frequency-domain representation of an audio file;
- a bitstream unpacking module that unpacks a bitstream of the audio signal to separate a side information portion of the audio signal from a main data portion of the audio signal 6+;
- a Huffman decoding module that decodes the main portion of the data;
- an inverse quantization module that executes inverse quantization on the decoded data to form a frequency-domain representation of the audio file;
- a binning and compression module to bin the frequency-domain representation of the audio file and compress the binned data to form a compressed frequency domain value file;
- and
- an output module to transmit the compressed frequency domain value file to a server to identify the audio file.
Dependencies are inferred from the claim text.