# US 2025/0085708 A1 · System and method to improve precision and recall of prototypical networks for sound event detection > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0085708 A1 - Document ID: US20250085708A1 - Status: Published application - Kind: A1 - Application number: 18/244,029 - Filed: 2023-09-08 - Published: 2025-03-13 - Earliest claimed: 2023-09-08 - Assignees: Robert Bosch GmbH - Applicants: Robert Bosch GmbH - Inventors: Md Ehsanul Haque Nirjhar; Luca Bondi; Shabnam Ghaffarzadegan; Samarjit Das - Web page: https://patentgrep.com/patent/US20250085708A1 ## CPC - G05D 1/0255: {using acoustic signals, e.g. ultra-sonic singals (sonar systems designed for anti-collision purposes G01S15/93)} - G05B 13/027: {using neural networks only} - G10L 17/26: Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices - G10L 25/30: using neural networks - G10L 25/51: for comparison or discrimination - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract A method of training a prototypical network for sound event detection includes receiving samples of an audio signal that include positive samples corresponding to sound events and negative samples that do not correspond to sound events, determining, based on the positive samples, respective positive prototypes of a plurality of classes of sound events, determining, based on the negative samples, respective negative prototypes for respective groups of the negative samples, each of the negative prototypes corresponding to a combination of a plurality of the negative samples, and generating, based on comparisons between a first sample and the respective positive prototypes and each of the negative prototypes, an output signal that indicates whether the first sample belongs to one of the plurality of classes of sound events. ## Claims ### Claim 1 A method of training a prototypical network for sound event detection, the method comprising: receiving samples of an audio signal, wherein the samples include positive samples corresponding to sound events and negative samples that do not correspond to sound events; determining, based on the positive samples, respective positive prototypes of a plurality of classes of sound events; determining, based on the negative samples, respective negative prototypes for respective groups of the negative samples, wherein each of the negative prototypes corresponds to a combination of a plurality of the negative samples; and generating, based on comparisons between (i) a first sample and (ii) the respective positive prototypes and each of the negative prototypes, an output signal that indicates whether a first sample belongs to one of the plurality of classes of sound events. ### Claim 2 (depends on 1) The method of claim 1, further comprising: obtaining first embeddings of the positive samples and second embeddings of the negative samples; determining the respective positive prototypes based on the first embeddings; and determining the respective negative prototypes based on the second embeddings. ### Claim 3 (depends on 1) The method of claim 1, wherein determining the respective negative prototypes includes determining a negative prototype for each of the respective groups of the negative samples. ### Claim 4 (depends on 1) The method of claim 1, further comprising: determining, based on the comparisons, at least one probability that the first sample corresponds to the one of the plurality of classes of sound events; and generating the output based on the at least one probability. ### Claim 5 (depends on 4) The method of claim 4, further comprising: determining at least one probability distribution; and generating the output based on the at least one probability distribution. ### Claim 6 (depends on 5) The method of claim 5, further comprising: determining at least one threshold based on the at least one probability distribution; and generating the output based on a comparison between the at least one probability and the at least one threshold. ### Claim 7 (depends on 6) The method of claim 6, wherein determining the at least one threshold includes determining the at least one threshold based on (i) a first probability distribution of probabilities that the positive samples belong to respective classes of the plurality of classes of sound events and (ii) a second distribution of probabilities that the negative samples belong to respective classes of the plurality of classes of sound events. ### Claim 8 A computing device configured to train a prototypical network for sound event detection, the computing device including a processing device configured to execute instructions stored in memory to: receive samples of an audio signal, wherein the samples include positive samples corresponding to sound events and negative samples that do not correspond to sound events; determine, based on the positive samples, respective positive prototypes of a plurality of classes of sound events; determine, based on the negative samples, respective negative prototypes for respective groups of the negative samples, wherein each of the negative prototypes corresponds to a combination of a plurality of the negative samples; and generate, based on comparisons between (i) a first sample and (ii) the respective positive prototypes and each of the negative prototypes, an output signal that indicates whether the first sample belongs to one of the plurality of classes of sound events. ### Claim 9 (depends on 8) The computing device of claim 8, wherein the processing device is further configured to execute the instructions to: obtain first embeddings of the positive samples and second embeddings of the negative samples; determine the respective positive prototypes based on the first embeddings; and determine the respective negative prototypes based on the second embeddings. ### Claim 10 (depends on 8) The computing device of claim 8, wherein determining the respective negative prototypes includes determining a negative prototype for each of the respective groups of the negative samples. ### Claim 11 (depends on 8) The computing device of claim 8, wherein the processing device is further configured to execute the instructions to: determine, based on the comparisons, at least one probability that the first sample corresponds to the one of the plurality of classes of sound events; and generate the output based on the at least one probability. ### Claim 12 (depends on 11) The computing device of claim 11, wherein the processing device is further configured to execute the instructions to: determine at least one probability distribution; and generate the output based on the at least one probability distribution. ### Claim 13 (depends on 12) The computing device of claim 12, wherein the processing device is further configured to execute the instructions to: determine at least one threshold based on the at least one probability distribution; and generate the output based on a comparison between the at least one probability and the at least one threshold. ### Claim 14 (depends on 13) The computing device of claim 13, wherein determining the at least one threshold includes determining the at least one threshold based on (i) a first probability distribution of probabilities that the positive samples belong to respective classes of the plurality of classes of sound events and (ii) a second distribution of probabilities that the negative samples belong to respective classes of the plurality of classes of sound events. ### Claim 15 A computer-controlled machine, comprising: at least one sensor configured to generate an audio signal; a control system configured to receive a first sample of the audio signal, and generate, based on comparisons between the (i) the first sample and (ii) respective positive prototypes for each of a plurality of classes of sound events and respective negative prototypes for each of a plurality of groups of negative prototypes, an output signal that indicates whether the first sample of the audio signal belongs to one of the plurality of classes of sound events; and an actuator configured to control an operation of the computer-controlled machine in response to the output of the control system. ### Claim 16 (depends on 15) The computer-controlled machine of claim 15, further comprising memory that stores the respective positive prototypes and the respective negative prototypes, wherein: the respective positive prototypes correspond to a plurality of positive samples; and each of the respective negative prototypes corresponds to a combination of a plurality of negative samples. ### Claim 17 (depends on 15) The computer-controlled machine of claim 15, wherein generating the output includes calculating a probability that the first sample belongs to a first class of the plurality of classes of sound events or a first group of the plurality of groups. ### Claim 18 (depends on 17) The computer-controlled machine of claim 17, wherein generating the output includes comparing the probability to at least one threshold and generating the output based on the comparison. ### Claim 19 (depends on 18) The computer-controlled machine of claim 18, wherein the at least one threshold includes a plurality of thresholds corresponding to respective classes of the plurality of classes of sound events. ### Claim 20 (depends on 15) The computer-controlled machine of claim 15, wherein the computer-controlled machine includes an autonomous robot.