# US 10,770,091 B2 · Blind source separation using similarity measure > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,770,091 B2 - Document ID: US10770091B2 - Status: Granted - Kind: B2 - Application number: 15/412,812 - Filed: 2017-01-23 - Published: 2018-06-28 - Granted: 2020-09-08 - Earliest claimed: 2016-12-28 - Assignees: Google Inc. - Applicants: Google Inc. - Inventors: Willem Bastiaan Kleijn; Sze Chie Lim - Web page: https://patentgrep.com/patent/US10770091B2 ## CPC - G10L 21/0308: characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques - G10L 21/028: using properties of sound source - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract A method includes: receiving time instants of audio signals generated by a set of microphones at a location; determining a distortion measure between frequency components of at least some of the received audio signals; determining a similarity measure for the frequency components using the determined distortion measure; and processing the audio signals based on the determined similarity measure. ## Claims ### Claim 1 A method comprising: receiving time instants of electronic audio signals generated by a set of microphones at a location; determining a distortion measure between frequency components of at least some of the received electronic audio signals; determining similarity measures for the frequency components using the determined distortion measure, the similarity measures measuring a similarity of the electronic audio signals at different time instants for respective frequency bins; and performing blind source separation of the electronic audio signals, the blind source separation including processing the electronic audio signals based on the determined similarity measure, including aggregating the similarity measures over a frequency band corresponding to the frequency bins. ### Claim 2 (depends on 1) The method of claim 1, wherein determining the distortion measure comprises determining a correlation measure of vector directionality that relates events at different times. ### Claim 3 (depends on 2) The method of claim 2, wherein the correlation measure includes a distance computation based on inner product. ### Claim 4 (depends on 1) The method of claim 1, wherein the similarity measures comprise kernelized similarity measures. ### Claim 5 (depends on 1) The method of claim 1, further comprising applying a weighting to the similarity measures, the weighting corresponding to relative importance across a band of frequency components for a time pair. ### Claim 6 (depends on 1) The method of claim 1, the method further comprising generating a similarity matrix for the frequency components based on the determined similarity measures. ### Claim 7 (depends on 6) The method of claim 6, further comprising performing clustering using the generated similarity matrix, the clustering indicating for which time segments a particular cluster is active, the cluster corresponding to a source of sound at the location. ### Claim 8 (depends on 7) The method of claim 7, wherein performing the clustering comprises performing centroid-based clustering. ### Claim 9 (depends on 7) The method of claim 7, wherein performing the clustering comprises performing exemplar-based clustering. ### Claim 10 (depends on 7) The method of claim 7, further comprising using the clustering to perform demixing in time. ### Claim 11 (depends on 7) The method of claim 7, further comprising using the clustering as a pre-processing step. ### Claim 12 (depends on 11) The method of claim 11, further comprising computing a mixing matrix for each frequency and then determining a demixing matrix from the mixing matrix. ### Claim 13 (depends on 12) The method of claim 12, wherein determining the demixing matrix comprises using a pseudo-inverse of the mixing matrix. ### Claim 14 (depends on 12) The method of claim 12, wherein determining the demixing matrix comprises using a minimum-variance demixing. ### Claim 15 (depends on 1) The method of claim 1, wherein the processing of the audio signals comprises speech recognition of participants. ### Claim 16 (depends on 1) The method of claim 1, wherein the processing of the audio signals comprises performing a search of the electronic audio signal for audio content from a participant. ### Claim 17 A computer program product tangibly embodied in a non-transitory storage medium, the computer program product including instructions that when executed cause a processor to perform operations including: receiving time instants of audio signals generated by a set of microphones at a location; determining a distortion measure between frequency components of at least some of the received audio signals; determining similarity measures for the frequency components using the determined distortion measure, the similarity measures measuring a similarity of the audio signals at different time instants for respective frequency bins; and performing blind source separation of the audio signals, the blind source separation including processing the audio signals based on the determined similarity measure, including aggregating the similarity measures over a frequency band corresponding to the frequency bins. ### Claim 18 (depends on 17) The computer program product of claim 17, wherein the similarity measures comprise kernelized similarity measures. ### Claim 19 A system comprising: a processor; and a computer program product tangibly embodied in a non-transitory storage medium, the computer program product including instructions that when executed cause the processor to perform operations including: receiving time instants of audio signals generated by a set of microphones at a location; determining a distortion measure between frequency components of at least some of the received audio signals; determining similarity measures for the frequency components using the determined distortion measure, the similarity measures measuring a similarity of the audio signals at different time instants for respective frequency bins; and performing blind source separation of the audio signals, the blind source separation including processing the audio signals based on the determined similarity measure, including aggregating the similarity measures over a frequency band corresponding to the frequency bins. ### Claim 20 (depends on 19) The system of claim 19, wherein the similarity measures comprise kernelized similarity measures.