# US 2017/0256271 A1 · Systems and methods facilitating selective removal of content from a mixed audio recording > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0256271 A1 - Document ID: US20170256271A1 - Status: Published application - Kind: A1 - Application number: 15/600,321 - Filed: 2017-05-19 - Published: 2017-09-07 - Earliest claimed: 2013-08-21 - Assignees: Google Inc. - Applicants: Google Inc. - Inventors: Richard Francis Lyon; Ron Weiss; Thomas Chadwick Walters - Web page: https://patentgrep.com/patent/US20170256271A1 ## CPC - G10L 21/0356: for synchronising with other signals, e.g. video signals - G06F 21/10: Protecting distributed programs or content, e.g. vending or licensing of copyrighted material (protection in video systems or pay television H04N7/16) {; Digital rights management [DRM]} - G10L 21/02: Speech enhancement, e.g. noise reduction or echo cancellation (reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08) - G10L 21/0272: Voice signal separating - G10L 21/028: using properties of sound source - G10L 21/0308: characterised by the type of parameter measurement, e.g. correlation techniques, zero crossing techniques or predictive techniques - G10L 21/0388: Details of processing therefor - G10L 25/51: for comparison or discrimination - H04N 21/4334: {Recording operations (recording of a television signal H04N5/76; arrangements for recording or accumulating broadcast information or broadcast-related information H04H60/27)} - H04N 21/4394: {involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams (arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58)} - H04N 21/8113: {comprising music, e.g. song in MP3 format} - G10L 2021/02087: {the noise being separate speech, e.g. cocktail party} - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Systems and methods facilitating removal of content from audio files are described. A method includes identifying a sound recording in a first audio file, identifying a reference file having at least a defined level of similarity to the sound recording, and processing the first audio file to remove the sound recording and generate a second audio file. In some embodiments, winner-take-all coding and Hough transforms are employed for determining alignment and rate adjustment of the reference file in the first audio file. After alignment, the reference file is filtered in the frequency domain to increase similarity between the reference file and the sound recording. The frequency domain representation (FR) of the filtered version is subtracted from the FR first audio and the result converted to a time representation of the second audio file. In some embodiments, spectral subtraction is also performed to generate a further improved second audio file. ## Claims ### Claim 1 A method for modifying content, the method comprising: receiving, using a hardware processor, a media content item that includes an audio portion having a plurality of sound recordings; identifying a reference file having sound recordings that are similar to a sound recording of the plurality of sound recordings in the media content item; aligning the reference file with the sound recording contained in the audio portion; and generating an updated media content item by modifying the sound recording from the audio portion of the media content item based on the aligning. ### Claim 2 (depends on 1) The method of claim 1, wherein the sound recording in the updated media content item is modified by removing the sound recording from the audio portion of the media content item. ### Claim 3 (depends on 1) The method of claim 1, further comprising determining that the received media content item is not accepted by a content server, wherein the sound recording in the updated media content item is modified in response to determining that the received media content item is not accepted by the content server by removing the sound recording from the audio portion of the media content item such that the updated media content item is accepted by the content server. ### Claim 4 (depends on 1) The method of claim 1, further comprising determining that the sound recording corresponding to a particular sound that is designed as an undesirable sound, wherein the sound recording in the updated media content item is modified in response to determining that the sound recording corresponding to the particular sound by attenuating an audio level associated with the sound recording from the audio portion of the media content item such that the sound recording is filtered out from the plurality of sound recordings. ### Claim 5 (depends on 1) The method of claim 1, wherein the sound recording in the updated media content item is modified by amplifying an audio level associated with the sound recording from the audio portion of the media content item. ### Claim 6 (depends on 1) The method of claim 1, wherein the sound recording in the updated media content item is modified by replacing the sound recording from the audio portion of the media content item with a replacement sound recording. ### Claim 7 (depends on 1) The method of claim 1, further comprising determining that the sound recording from the audio portion of the media content item corresponds to a particular speaker within the audio portion of the media content item, wherein the sound recording in the updated media content item is modified by amplifying the sound recording corresponding to the particular speaker. ### Claim 8 (depends on 1) The method of claim 1, wherein the reference file is aligned with the sound recording based on a comparison of a spectrogram of the reference file and a spectrogram of the audio portion of the media content item. ### Claim 9 (depends on 1) The method of claim 1, wherein the reference file is aligned with the sound recording based on a comparison of a winter-take-all (WTA)-coded spectrogram of the reference file and a WTA-coded spectrogram of the audio portion of the media content item. ### Claim 10 (depends on 1) The method of claim 1, wherein the reference file is aligned with the sound recording by mapping, into a Hough space, one or more estimated time offsets between the reference file and the audio portion of the media content item. ### Claim 11 (depends on 1) The method of claim 1, wherein aligning the reference file with the sound recording contained in the audio portion further comprises determining a rate adjustment between the reference file and the audio portion of the media content item by mapping, into a Hough space, one or more estimated rate stretch factors between the reference file and the audio portion of the media content item. ### Claim 12 (depends on 11) The method of claim 11, further comprising selecting an estimated time offset from the one or more estimated time offsets and an estimated rate stretch factor from the one or more estimated rate stretch factors based on the mapping into the Hough space. ### Claim 13 (depends on 1) The method of claim 1, further comprising filtering the reference file in a frequency domain to generate a filtered frequency domain representation of the reference file, wherein a similarity between the filtered frequency domain representation of the reference file and a frequency domain representation of the sound recording is greater than a similarity between a frequency domain representation of the reference file and a frequency domain representation of the sound recording. ### Claim 14 (depends on 13) The method of claim 13, further comprising: subtracting the filtered frequency domain representation of the reference file from the frequency domain representation of the audio file to generate a frequency domain representation of the updated media content item; and converting the frequency domain representation of the updated media content item to the updated media content item. ### Claim 15 (depends on 13) The method of claim 13, further comprising: subtracting the filtered frequency domain representation of the reference file from the frequency domain representation of the audio file to generate a frequency domain representation of an intermediate audio file; performing spectral subtraction in the frequency domain on the frequency domain representation of the intermediate audio file to generate a frequency domain representation of the updated media content item; and converting the frequency domain representation of the updated media content item to the updated media content item. ### Claim 16 (depends on 1) The method of claim 1, further comprising causing an interface to be presented that includes options for selecting a replacement sound recording from a plurality of replacement sound records, wherein, in response to receiving a selection of the replacement sound recording from the interface, the updated media content item is generated by replacing the sound recording with the replacement sound recording based on the aligning. ### Claim 17 (depends on 1) The method of claim 1, further comprising causing an interface to be presented that includes an option for selecting a replacement sound recording from a plurality of replacement sound records, wherein, in response to receiving a selection of the replacement sound recording from the interface, the updated media content item is generated by replacing the sound recording with the replacement sound recording based on the aligning. ### Claim 18 (depends on 1) The method of claim 1, further comprising causing an interface to be presented that includes a plurality of options for modifying the sound recording from the audio portion of the media content item, wherein, in response to receiving a selected option from the interface, the updated media content item is generated by modifying the sound recording from the audio portion of the media content item based on the aligning and based on the selected option. ### Claim 19 A system for modifying content, the system comprising: a hardware processor that is configured to: receive a media content item that includes an audio portion having a plurality of sound recordings; identify a reference file having sound recordings that are similar to a sound recording of the plurality of sound recordings in the media content item; align the reference file with the sound recording contained in the audio portion; and generate an updated media content item by modifying the sound recording from the audio portion of the media content item based on the aligning. ### Claim 20 A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method for modifying content, the method comprising: receiving a media content item that includes an audio portion having a plurality of sound recordings; identifying a reference file having sound recordings that are similar to a sound recording of the plurality of sound recordings in the media content item; aligning the reference file with the sound recording contained in the audio portion; and generating an updated media content item by modifying the sound recording from the audio portion of the media content item based on the aligning.