# US 10,872,600 B1 · Background audio identification for speech disambiguation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,600 B1 - Document ID: US10872600B1 - Status: Granted - Kind: B1 - Application number: 16/249,211 - Filed: 2019-01-16 - Granted: 2020-12-22 - Earliest claimed: 2012-06-01 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Jason Sanders; Gabriel Taubman; John J. Lee - Web page: https://patentgrep.com/patent/US10872600B1 ## CPC - G10L 15/08: Speech classification or search - G06F 16/685: {using automatically derived transcript of audio data, e.g. lyrics (speech recognition G10L15/00)} - G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning} - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 21/0272: Voice signal separating - G10L 25/48: specially adapted for particular use - H04M 3/4936: {Speech interaction details (speech recognition per se G10L15/00)} - G10L 21/0208: Noise filtering - G10L 2015/225: {Feedback of the input speech} - H04M 2201/40: using speech recognition - H04M 2203/352: In-call/conference information service - 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) - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) ## Abstract Implementations relate to techniques for providing context-dependent search results. A computer-implemented method includes receiving an audio stream at a computing device during a time interval, the audio stream comprising user speech data and background audio, separating the audio stream into a first substream that includes the user speech data and a second substream that includes the background audio, identifying concepts related to the background audio, generating a set of terms related to the identified concepts, influencing a speech recognizer based on at least one of the terms related to the background audio, and obtaining a recognized version of the user speech data using the speech recognizer. ## Claims ### Claim 1 A method comprising: receiving, at a voice recognition system, first audio data and second audio data from a computing device associated with a user, the computing device configured to: capture an audio stream comprising the first audio data and the second audio data; separate the first audio data and the second audio data from the captured audio stream; and provide the first audio data and the second audio data to the voice recognition system; processing, by the voice recognition system, the second audio data to generate at least one term associated with the second audio data; influencing, by the voice recognition system, a speech recognition model based on the at least one term associated with the second audio data; and after influencing the speech recognition model, transcribing, by the voice recognition system, the first audio data into a textual representation using the speech recognition model. ### Claim 2 (depends on 1) The method of claim 1, wherein the first audio data corresponds to an utterance spoken by the user and the second audio data corresponds to background audio from one or more background audio sources proximate to the user. ### Claim 3 (depends on 2) The method of claim 2, wherein the one or more background audio sources comprise at least one of a radio, a television, ambient background noise, or conversations between people other than the user. ### Claim 4 (depends on 1) The method of claim 1, wherein the computing device is configured to separate the first audio data and the second audio data from the captured audio stream by separating the captured audio stream into a first substream and a second substream, the first substream corresponding to the first audio data and the second substream isolated from the first substream and corresponding to the second audio data. ### Claim 5 (depends on 4) The method of claim 4, wherein the computing device is configured to provide the first audio data and the second audio data to the voice recognition system by transmitting the first substream and the second substream over a communication channel to the voice recognition system. ### Claim 6 (depends on 1) The method of claim 1, further comprising transmitting the textual representation of the first audio data to the computing device, the textual representation when received by the computing device causing the computing device to display the textual representation on a display. ### Claim 7 (depends on 1) The method of claim 1, further comprising transmitting the textual representation of the first audio data to the computing device, the textual representation when received by the computing device causing the computing device to perform a particular task based on the textual representation. ### Claim 8 (depends on 1) The method of claim 1, wherein at least a portion of the first audio data and at least a portion of the second audio data of the audio stream are captured by the computing device during a same time interval. ### Claim 9 (depends on 1) The method of claim 1, wherein at least a portion of the second audio data of the audio stream is captured by the computing device during a time interval that commences before the computing device captures the first audio data. ### Claim 10 (depends on 1) The method of claim 1, wherein at least a portion of the second audio data of the audio stream is captured by the computing device during a time interval that commences after the computing device captures the first audio data. ### Claim 11 (depends on 1) The method of claim 1, wherein processing the second audio data to generate the at least one term associated with the second audio data comprises: identifying one or more concepts from audio features of the second audio data; and generating a set of terms related to the identified one or more concepts. ### Claim 12 (depends on 11) The method of claim 11, wherein generating the set of terms related to the identified one or more concepts comprises querying a conceptual expansion database for the set of terms using the one or more concepts identified from the audio features of the second audio data. ### Claim 13 (depends on 1) The method of claim 1, wherein influencing the speech recognition model based on the at least one term associated with the second audio data comprises adjusting a probability or relevance score associated with the speech recognition model recognizing the at least one term associated with the second audio data. ### Claim 14 (depends on 13) The method of claim 13, further comprising: generating, by the voice recognition system, conceptual bias data using the at least one term associated with the second audio data; and adjusting, by the voice recognition system, the probability or relevance score associated with the speech recognition model recognizing the at least one term associated with the second audio data based on the conceptual bias data. ### Claim 15 (depends on 14) The method of claim 14, wherein transcribing the first audio data into the textual representation using the speech recognition model comprises, selecting, by the speech recognition model, the textual representation from a set of textual representations that have substantially similar frequencies of occurrence in a particular language by using the conceptual bias data to weigh a statistical selection of the textual representation from the set of textual representations. ### Claim 16 A voice recognition system comprising: data processing hardware; and memory hardware in communication with the data processing hardware and storing instructions, that when executed by the data processing hardware, cause the data processing hardware to perform operations comprising: receiving first audio data and second audio data from a computing device associated with a user, the computing device configured to: capture an audio stream comprising the first audio data and the second audio data; separate the first audio data and the second audio data from the captured audio stream; and provide the first audio data and the second audio data to the voice recognition system; processing the second audio data to generate at least one term associated with the second audio data; influencing a speech recognition model based on the at least one term associated with the second audio data; and after influencing the speech recognition model, transcribing the first audio data into a textual representation using the speech recognition model. ### Claim 17 (depends on 16) The voice recognition system of claim 16, wherein the first audio data corresponds to an utterance spoken by the user and the second audio data corresponds to background audio from one or more background audio sources proximate to the user. ### Claim 18 (depends on 17) The voice recognition system of claim 17, wherein the one or more background audio sources comprise at least one of a radio, a television, ambient background noise, or conversations between people other than the user. ### Claim 19 (depends on 16) The voice recognition system of claim 16, wherein the computing device is configured to separate the first audio data and the second audio data from the captured audio stream by separating the captured audio stream into a first substream and a second substream, the first substream corresponding to the first audio data and the second substream isolated from the first substream and corresponding to the second audio data. ### Claim 20 (depends on 19) The voice recognition system of claim 19, wherein the computing device is configured to provide the first audio data and the second audio data to the voice recognition system by transmitting the first substream and the second substream over a communication channel to the voice recognition system. ### Claim 21 (depends on 16) The voice recognition system of claim 16, wherein the operations further comprise transmitting the textual representation of the first audio data to the computing device, the textual representation when received by the computing device causing the computing device to display the textual representation on a display. ### Claim 22 (depends on 16) The voice recognition system of claim 16, wherein the operations further comprise transmitting the textual representation of the first audio data to the computing device, the textual representation when received by the computing device causing the computing device to perform a particular task based on the textual representation. ### Claim 23 (depends on 16) The voice recognition system of claim 16, wherein at least a portion of the first audio data and at least a portion of the second audio data are captured by the computing device during a same time interval. ### Claim 24 (depends on 16) The voice recognition system of claim 16, wherein at least a portion of the second audio data is captured by the computing device during a time interval that commences before the computing device captures the first audio data. ### Claim 25 (depends on 16) The voice recognition system of claim 16, wherein at least a portion of the second audio data is captured by the computing device during a time interval that commences after the computing device captures the first audio data. ### Claim 26 (depends on 16) The voice recognition system of claim 16, wherein processing the second audio data to generate the at least one term associated with the second audio data comprises: identifying one or more concepts from audio features of the second audio data; and generating a set of terms related to the identified one or more concepts. ### Claim 27 (depends on 26) The voice recognition system of claim 26, wherein generating the set of terms related to the identified one or more concepts comprises querying a conceptual expansion database for the set of terms using the one or more concepts identified from the audio features of the second audio data. ### Claim 28 (depends on 16) The voice recognition system of claim 16, wherein influencing the speech recognition model based on the at least one term associated with the second audio data comprises adjusting a probability or relevance score associated with the speech recognition model recognizing the at least one term associated with the second audio data. ### Claim 29 (depends on 28) The voice recognition system of claim 28, wherein the operations further comprise: generating conceptual bias data using the at least one term associated with the second audio data; and adjusting the probability or relevance score associated with the speech recognition model recognizing the at least one term associated with the second audio data based on the conceptual bias data. ### Claim 30 (depends on 29) The voice recognition system of claim 29, wherein transcribing the first audio data into the textual representation comprises, selecting, by the speech recognition model, the textual representation from a set of textual representations that have substantially similar frequencies of occurrence in a particular language by using the conceptual bias data to weigh a statistical selection of the textual representation from the set of textual representations.