# US 12,015,655 B2 · Method and system for handling a teleconference > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,015,655 B2 - Document ID: US12015655B2 - Status: Granted - Kind: B2 - Application number: 18/039,026 - Filed: 2021-01-18 - Published: 2023-12-28 - Granted: 2024-06-18 - Earliest claimed: 2021-01-18 - Assignees: Telefonaktiebolaget LM Ericsson (publ) - Applicants: Telefonaktiebolaget LM Ericsson (publ) - Inventors: Tommy Arngren; Tommy Falk; Andreas Kristensson; Peter Ökvist - Web page: https://patentgrep.com/patent/US12015655B2 ## CPC - H04L 12/1822: {Conducting the conference, e.g. admission, detection, selection or grouping of participants, correlating users to one or more conference sessions, prioritising transmission} - H04L 65/403: Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) - G10L 15/02: Feature extraction for speech recognition; Selection of recognition unit - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 21/034: Automatic adjustment - G10L 21/0364: for improving intelligibility - H04L 12/1831: {Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status} - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract A method performed by a system of a communication network includes obtaining digital representations of speech detected from communication devices connected to a teleconference, and receiving a request for a parallel discussion from a first of the communication devices with a subgroup of the communication devices. Further, the system sets up a parallel discussion group for the first communication device and the subgroup of communication devices, provides the digital representations of speech of the first communication device and the subgroup of communication devices only to the devices of the parallel discussion group so that each device of the parallel discussion group is able to play back the digital representations of speech of the other devices of the parallel discussion group, and provides the digital representations of speech of the plurality of communication devices except the first communication device and the subgroup of communication devices. ## Claims ### Claim 1 A method performed by a system of a communication network for handling a teleconference, the method comprising: obtaining digital representations of speech detected from sound captured at a microphone of each of a plurality of communication devices connected to the teleconference; receiving, after the obtaining, a request for a parallel discussion from a first of the plurality of communication devices connected to the teleconference, the request for a parallel discussion being with a subgroup of the plurality of communication devices connected to the teleconference; based on the received request, setting up a parallel discussion group for the first communication device and the subgroup of communication devices, which parallel discussion group is at least partly separated from the teleconference, providing the digital representations of speech of the first communication device and the subgroup of communication devices only to the devices of the parallel discussion group so that each device of the parallel discussion group is able to play back the digital representations of speech of the other devices of the parallel discussion group, and providing the digital representations of speech of the plurality of communication devices except the first communication device and the subgroup of communication devices, called remaining teleconference communication devices, to the plurality of communication devices so that each device of the plurality of communication devices is able to play back the digital representations of speech of the other devices of the remaining teleconference communication devices. ### Claim 2 (depends on 1) Method according to claim 1, further comprising, before and when receiving the request for a parallel discussion, providing the digital representations of speech of the plurality of communication devices to the plurality of communication devices so that each device of the plurality of communication devices is able to play back the digital representations of speech of the other devices of the plurality of communication devices. ### Claim 3 (depends on 1) Method according to claim 1, wherein the providing the digital representations of speech of the first communication device and the subgroup of communication devices is provided to the devices of the parallel discussion group with a higher gain control value than the digital representations of speech provided to the remaining teleconference communication devices. ### Claim 4 (depends on 1) Method according to claim 1, further comprising, in response to the receiving of a request for a parallel discussion from the first communication device, sending a request to the subgroup of the communication devices whether each of them wants to join the parallel discussion, and only setting up the parallel discussion group for the communication devices of the subgroup for which a positive response is received. ### Claim 5 (depends on 1) Method according to claim 1, further comprising: storing the digital representations of speech of the first communication device and the subgroup of communication devices, and optionally, providing the remaining teleconference communication devices access to the stored digital representations of speech of the first communication device and the subgroup of communication devices. ### Claim 6 (depends on 1) Method according to claim 1, further comprising: conditionally providing the digital representations of speech of the first communication device and the subgroup of communication devices, or information of the digital representations of speech of the first communication device and the subgroup of communication devices to the remaining teleconference communication devices depending on a group privacy information or individual privacy information for the subgroup and the first communication device. ### Claim 7 (depends on 1) Method according to claim 1, further comprising: determining features for the received digital representations of speech of the communication devices of the parallel discussion group, based on speech analysis of the received digital representations of speech, the features comprising one or more of conversation topics, key words, and tone of words. ### Claim 8 (depends on 1) Method according to claim 1, wherein the plurality of communication devices connected to the teleconference are handled by a first instance of a Machine Learning Model, MLM, of the system, and wherein the setting up of a parallel discussion group for the first communication device and the subgroup of communication devices comprises setting up a second instance of the MLM and hereinafter handling the first communication device and the subgroup of communication devices by the second instance of the MLM and not by the first instance. ### Claim 9 A system operable in a wireless communication system and configured for handling a teleconference, the system comprising a processing circuitry and a memory, said memory containing instructions executable by said processing circuitry, whereby the system is operative for: obtaining digital representations of speech detected from sound captured at a microphone of each of a plurality of communication devices connected to the teleconference; receiving, after the obtaining, a request for a parallel discussion from a first of the plurality of communication devices connected to the teleconference, the request for a parallel discussion being with a subgroup of the plurality of communication devices connected to the teleconference; based on the received request, setting up a parallel discussion group for the first communication device and the subgroup of communication devices, which parallel discussion group is at least partly separated from the teleconference, providing the digital representations of speech of the first communication device and the subgroup of communication devices only to the devices of the parallel discussion group so that each device of the parallel discussion group is able to play back the digital representations of speech of the other devices of the parallel discussion group, and providing the digital representations of speech of the plurality of communication devices except the first communication device and the subgroup of communication devices, called remaining teleconference communication devices, to the plurality of communication devices so that each device of the plurality of communication devices is able to play back the digital representations of speech of the other devices of the remaining teleconference communication devices. ### Claim 10 (depends on 9) System according to claim 9, further being operable for, before and when receiving the request for a parallel discussion, providing the digital representations of speech of the plurality of communication devices to the plurality of communication devices so that each device of the plurality of communication devices is able to play back the digital representations of speech of the other devices of the plurality of communication devices. ### Claim 11 (depends on 9) System according to claim 9, wherein the providing the digital representations of speech of the first communication device and the subgroup of communication devices is provided to the devices of the parallel discussion group with a higher gain control value than the digital representations of speech provided to the remaining teleconference communication devices. ### Claim 12 (depends on 9) System according to claim 9, further being operable for, in response to the receiving of a request for a parallel discussion from the first communication device, sending a request to the subgroup of the communication devices whether each of them wants to join the parallel discussion, and only setting up the parallel discussion group for the communication devices of the subgroup for which a positive response is received. ### Claim 13 (depends on 9) System according to claim 9, further being operable for: storing the digital representations of speech of the first communication device and the subgroup of communication devices, and optionally, providing the remaining teleconference communication devices access to the stored digital representations of speech of the first communication device and the subgroup of communication devices. ### Claim 14 (depends on 9) System according to claim 9, further being operable for: conditionally providing the digital representations of speech of the first communication device and the subgroup of communication devices, or information of the digital representations of speech of the first communication device and the subgroup of communication devices to the remaining teleconference communication devices depending on a group privacy information or individual privacy information for the subgroup and the first communication device. ### Claim 15 (depends on 9) System according to claim 9, further being operable for: determining features for the received digital representations of speech of the communication devices of the parallel discussion group, based on speech analysis of the received digital representations of speech, the features comprising one or more of conversation topics, key words, and tone of words. ### Claim 16 (depends on 9) System according to claim 9, further comprising a first instance and a second instance of a Machine Learning Model, MLM, the system being operative for handling the plurality of communication devices connected to the teleconference by the first instance of the MLM, and wherein the system is operative for performing the setting up of the parallel discussion group for the first communication device and the subgroup of communication devices by setting up the second instance of the MLM, and thereafter handling the first communication device and the subgroup of communication devices by the second instance of the MLM and not by the first instance. ### Claim 17 A computer program comprising a non-transitory computer readable medium storing instructions, which, when executed by at least one processing circuitry of a system of a wireless communication network, configured for handling a teleconference, causes the system to perform the following steps: obtaining digital representations of speech detected from sound captured at a microphone of each of a plurality of communication devices connected to the teleconference; receiving, after the obtaining, a request for a parallel discussion from a first of the plurality of communication devices connected to the teleconference, the request for a parallel discussion being with a subgroup of the plurality of communication devices connected to the teleconference; based on the received request, setting up a parallel discussion group for the first communication device and the subgroup of communication devices, which parallel discussion group is at least partly separated from the teleconference, providing the digital representations of speech of the first communication device and the subgroup of communication devices only to the devices of the parallel discussion group so that each device of the parallel discussion group is able to play back the digital representations of speech of the other devices of the parallel discussion group, and providing the digital representations of speech of the plurality of communication devices except the first communication device and the subgroup of communication devices, called remaining teleconference communication devices, to the plurality of communication devices so that each device of the plurality of communication devices is able to play back the digital representations of speech of the other devices of the remaining teleconference communication devices.