Audio transcription for electronic conferencing
Inventors
MAURY, Christopher • FORREST, James A. • GARRIDO, Christopher M. • Miauton, Patrick
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12739142-B2
Publication Date
2026-09-15
Expiration Date
Abstract
Aspects of the subject technology provide for transcription of audio content during a conferencing session, such as an audio conferencing session or a video conferencing session. The transcription can be generated by the device at which the audio input is received, and transmitted to a remote device at which the transcription is displayed. Video content can also be provided from the device that generates the transcription to the remote device that displays in the transcription. The transcription can be provided with time information corresponding to time information in the video content, for synchronized display of the transcription and the corresponding video content.
Core Innovation
A problem addressed is that, during a conferencing session between at least a first device and a second device, audio input is handled so that a first device can generate transcription and deliver it for use at the second device. The document describes generating a first transcription of a first audio input while the conferencing session is ongoing and sending the first transcription from the first device to the second device.
The transcription is generated by the first device using a voice model previously stored at the first device and trained on one or more voice inputs from a user of the first device. The document further describes sending transcription information associated with a corresponding audio stream, and providing transcription updates, including updates associated with an updated corresponding confidence score. It also describes transmitting the transcription integrated into a video stream.
The document additionally addresses cases in which the second device cannot generate the transcription. It describes providing, from the first device to the second device during the conferencing session, a request for a transcription of an audio input corresponding to the second device; determining that the second device is unable to generate the transcription; receiving an audio stream corresponding to the audio input at the first device; and generating the transcription of the audio stream received from the second device.
It further describes conditional generation of a transcription of an audio stream received from the second device at the first device in accordance with one or more criteria, where transcription is provided to a third device, including criteria based on computing capabilities and nomination among involved devices.
Claims Coverage
Independent claims: clm-00001, clm-00013, and clm-00017. The inventive features cover local transcription generation using a stored voice model, sending transcription during conferencing, confidence-score associated updates, multimedia-related transmission of transcription, fallback transcription when a device cannot transcribe, and conditional nomination or selection of which device generates transcription based on computing capabilities.
Generating and sending a transcription during a conferencing session using a stored voice model
During a conferencing session between at least a first device and a second device, receiving a first audio input; generating a first transcription of the first audio input by the first device using a voice model previously stored at the first device and having been trained on one or more voice inputs from a user of the first device; and sending the first transcription from the first device to the second device.
Requesting transcription when the second device is unable, receiving audio, and generating transcription at the first device
Providing, from a first device to a second device during a conferencing session, a request for a transcription of an audio input corresponding to the second device; determining by the first device that the second device is unable to generate the transcription of the audio input corresponding to the second device; receiving at the first device from the second device an audio stream corresponding to the audio input corresponding to the second device; and generating by the first device a transcription of the audio stream received from the second device.
Conditionally generating transcription of an audio stream received from another device and providing it to a third device based on criteria and computing capabilities
Receiving an audio stream at a first device from a second device during a conferencing session between at least the first device, the second device, and a third device; and in accordance with one or more criteria being met, generating by the first device a transcription corresponding to the audio stream from the second device and providing the transcription to the third device.
Across the independent claims, the document’s claim coverage centers on generating transcription at a first device during an active conferencing session, transmitting transcription to other participants, updating transcription with a confidence score, and handling device inability through a request and fallback flow. It also covers conditional transcription generation based on criteria that include computing capabilities and nomination among devices.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?