# US 12,223,935 B2 · Voice assistant system with audio effects related to voice commands > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,223,935 B2 - Document ID: US12223935B2 - Status: Granted - Kind: B2 - Application number: 17/395,822 - Filed: 2021-08-06 - Published: 2023-02-09 - Granted: 2025-02-11 - Earliest claimed: 2021-08-06 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Venkata Vara Prasad Karri; Saraswathi Sailaja Perumalla; Sarbajit K. Rakshit; Neela Vauhini Komaragiri - Web page: https://patentgrep.com/patent/US12223935B2 ## CPC - G06F 3/165: {Management of the audio stream, e.g. setting of volume, audio stream path} - G10H 1/366: {with means for modifying or correcting the external signal, e.g. pitch correction, reverberation, changing a singer's voice} - G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback} - G10H 1/0091: {Means for obtaining special acoustic effects (combined with modulation G10H1/043)} - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - H04R 5/04: Circuit arrangements, {e.g. for selective connection of amplifier inputs/outputs to loudspeakers, for loudspeaker detection, or for adaptation of settings to personal preferences or hearing impairments (combinations of amplifiers H03F3/68; stereophonic systems H04S)} - H04S 7/30: {Control circuits for electronic adaptation of the sound field} - G10H 2250/455: Gensound singing voices, i.e. generation of human voices for musical applications, vocal singing sounds or intelligible words at a desired pitch or with desired vocal effects, e.g. by phoneme synthesis - G10L 21/00: Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility (G10L19/00 takes precedence) - G10L 2015/223: {Execution procedure of a spoken command} - G10L 2015/225: {Feedback of the input speech} - H04S 2400/13: Aspects of volume control, not necessarily automatic, in stereophonic sound systems - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10H: ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K) - H04S: STEREOPHONIC SYSTEMS ## Abstract Voice command type entry used as a basis for applying “audio effects” (see definition herein), “sound effects” (see definition herein) and/or audio edits (see definition herein) to a sound signal. This may be done so that the various types of instructed audio processing evoke, in typical listeners, a desired sentiment or mood. Artificial intelligence may be used to accomplish this objective. ## Claims ### Claim 1 A computer implemented method (CIM) comprising: receiving, via a first computer, an input data set that includes audio data for an untreated audio track and an identification of a sentiment that is to be evoked when a user listens to the audio track; applying a first artificial intelligence algorithm stored in the first computer to the identification of the sentiment of the input data set to determine a set of audio effect(s) to be applied to the untreated audio track to obtain a treated audio track that tends to evoke the sentiment; applying, via sound processing performed by the first computer, the set of audio effect(s) to the untreated audio track to obtain the treated audio track that tends to evoke the sentiment; and presenting, via one or more audio speakers communicatively connected to the first computer, the treated audio track as sound to at least a first user. ### Claim 2 (depends on 1) The CIM of claim 1 further comprising: applying a second artificial intelligence algorithm stored in the first computer to the input data set to determine a set of added sound(s) to be added to the untreated audio track to obtain audio data corresponding to the treated audio track that tends to evoke the sentiment; and applying, via processing performed by the first computer, the set of added sound(s) to the untreated audio track as a part of the obtaining of the treated audio track that tends to evoke the sentiment. ### Claim 3 (depends on 1) The CIM of claim 1 wherein the input data set further includes a voice command containing natural language and the identification of the sentiment is derived directly from the natural language. ### Claim 4 (depends on 1) The CIM of claim 1 wherein the set of audio effect(s) includes at least one of the following types of audio effects: reverb, echo and/or phaser. ### Claim 5 (depends on 1) The CIM of claim 1 wherein the set of audio effect(s) includes at least one of the following types of audio effects: autotune, vocoder and/or voicebox. ### Claim 6 (depends on 1) The CIM of claim 1 wherein the set of audio effect(s) includes at least one of the following types of audio effects: a change in speed, a change in tempo, a change in key and/or a change in pitch. ### Claim 7 (depends on 1) The CIM of claim 1 wherein: the input data set further includes information indicative of an audio editing treatment; the CIM further comprising: determining a set of audio edit(s) to the untreated audio track based on the audio editing treatment; and editing the untreated audio track to make the audio editing treatment as part of the obtaining of the treated audio track. ### Claim 8 A computer program product (CPP) comprising: one or more computer-readable storage media; and program instructions stored on the one or more computer-readable storage media to perform operations comprising: receiving an input data set that includes audio data for an untreated audio track and an identification of a sentiment that is to be evoked when a user listens to the audio track; applying a first artificial intelligence algorithm to the identification of the sentiment of the input data set to determine a set of audio effect(s) to be applied to the untreated audio track to obtain a treated audio track that tends to evoke the sentiment; applying, via sound processing, the set of audio effect(s) to the untreated audio track to obtain the treated audio track that tends to evoke the sentiment; and presenting, via one or more audio speakers communicatively connected to a computer hosting the first artificial intelligence algorithm, the treated audio track as sound to at least a first user. ### Claim 9 (depends on 8) The CPP of claim 8, wherein the operations further comprise: applying a second artificial intelligence algorithm stored in the computer to the input data set to determine a set of added sound(s) to be added to the untreated audio track to obtain audio data corresponding to the treated audio track that tends to evoke the sentiment; and applying, via processing performed by the computer, the set of added sound(s) to the untreated audio track as a part of the obtaining of the treated audio track that tends to evoke the sentiment. ### Claim 10 (depends on 8) The CPP of claim 8, wherein the input data set further includes a voice command containing natural language and the identification of the sentiment is derived directly from the natural language. ### Claim 11 (depends on 8) The CPP of claim 8, wherein the set of audio effect(s) includes at least one of the following types of audio effects: reverb, echo and/or phaser. ### Claim 12 (depends on 8) The CPP of claim 8, wherein the set of audio effect(s) includes at least one of the following types of audio effects: autotune, vocoder and/or voicebox. ### Claim 13 (depends on 8) The CPP of claim 8, wherein the set of audio effect(s) includes at least one of the following types of audio effects: a change in speed, a change in tempo, a change in key and/or a change in pitch. ### Claim 14 (depends on 8) The CPP of claim 8, wherein the input data set further includes information indicative of an audio editing treatment, and the operations further comprise: determining a set of audio edit(s) to the untreated audio track based on the audio editing treatment; and editing the untreated audio track to make the audio editing treatment as part of the obtaining of the treated audio track. ### Claim 15 A computer system (CS) comprising: a processor set; one or more computer-readable storage media; one or more audio speakers communicatively connected to the processor set; and program instructions stored on the one or more computer-readable storage media to cause the processor set to perform operations comprising: receiving an input data set that includes audio data for an untreated audio track and an identification of a sentiment that is to be evoked when a user listens to the audio track; applying a first artificial intelligence algorithm to the identification of the sentiment of the input data set to determine a set of audio effect(s) to be applied to the untreated audio track to obtain a treated audio track that tends to evoke the sentiment; applying, via sound processing, the set of audio effect(s) to the untreated audio track to obtain the treated audio track that tends to evoke the sentiment; and presenting, via the one or more audio speakers, the treated audio track as sound to at least a first user. ### Claim 16 (depends on 15) The CS of claim 15, wherein the operations further comprise: applying a second artificial intelligence algorithm stored in the one or more computer-readable storage media to the input data set to determine a set of added sound(s) to be added to the untreated audio track to obtain audio data corresponding to the treated audio track that tends to evoke the sentiment; and applying, via processing performed by the processor set, the set of added sound(s) to the untreated audio track as a part of the obtaining of the treated audio track that tends to evoke the sentiment. ### Claim 17 (depends on 15) The CS of claim 15, wherein the input data set further includes a voice command containing natural language and the identification of the sentiment is derived directly from the natural language. ### Claim 18 (depends on 15) The CS of claim 15, wherein the set of audio effect(s) includes at least one of the following types of audio effects: reverb, echo and/or phaser. ### Claim 19 (depends on 15) The CS of claim 15, wherein the set of audio effect(s) includes at least one of the following types of audio effects: autotune, vocoder and/or voicebox. ### Claim 20 (depends on 15) The CS of claim 15, wherein the set of audio effect(s) includes at least one of the following types of audio effects: a change in speed, a change in tempo, a change in key and/or a change in pitch.