Cisco Technology, Inc.

Kareem Aladdin Nassar

David Abraham Wiener

Rishabh Gupta Yadav

Matthew James Ceravolo

Sylvain Le Groux

One embodiment of the present invention sets forth a technique for processing recordings of events. The technique includes applying a machine learning model to a plurality of samples from one or more recordings of the events to generate a plurality of embeddings representing the plurality of samples. The technique also includes generating a plurality of labels that identify speakers associated with the plurality of samples based on metadata comprising timestamps of voice activity during the events and participants associated with the voice activity. The technique further includes storing mappings of the plurality of embeddings to the plurality of labels.

Matching speakers to meeting audio

Presented herein are techniques for augmenting a speech recognition engine. According to the disclosed techniques, audio data is obtained as part of an automatic speech recognition session. Speech hints are also obtained as part of the automatic speech recognition session. A dynamic language model is generated from the speech hints for use during the automatic speech recognition session. A combined language model is then generated from the dynamic language model and a static language model. Finally, the audio data is converted to text using the combined language model as part of the automatic speech recognition session.

Speech recognition using on-the-fly-constrained language model per utterance

One embodiment of the present invention sets forth a technique for enhancing meeting participation by an interactive virtual assistant. The technique includes loading a resource for conducting the meeting over a teleconferencing system. The technique also includes configuring, based on the resource, virtual input/output (I/O) devices for integrating the interactive virtual assistant into the teleconferencing system during the meeting. In response to a command received over a first device in the virtual I/O devices, the technique further includes generating, by the interactive virtual assistant, output containing a response to the command over a second device in the virtual I/O devices.

Growing community of inventors

Fremont, CA, United States of America

Kareem Aladdin Nassar