Gong I.O has patented a method using visual information in a video stream of a teleconference to diarize speech. The system parses audio and video components, tags speech segments with speaker identification, and labels segments based on neural network analysis of visual information. GlobalData’s report on Gong I.O gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Gong I.O, Quantum machine learning was a key innovation area identified from patents. Gong I.O's grant share as of May 2024 was 34%. Grant share is based on the ratio of number of grants to total number of patents.
Speech diarization using visual information in recorded teleconferences
A recently granted patent (Publication Number: US11978456B2) outlines a method for utilizing visual information in a video stream of a recorded teleconference to diarize speech. The method involves obtaining components of the teleconference, including audio, video, teleconference metadata, and transcription data. The audio component is parsed into speech segments associated with timestamps and speaker identification information. These segments are tagged and diarized by indexing the transcription data and using a neural network to identify speaker information based on visual content, such as artificial visual representations not including faces or showing lips in the process of speaking. The method also includes analyzing the diarization results and providing them to a user for further insights.
Furthermore, the patent describes a method for diarizing speech in a teleconference using video content. Similar to the previous method, components of the teleconference are obtained, and the audio component is parsed into speech segments associated with timestamps and speaker identification information. These segments are tagged and diarized by indexing the transcription data and using a neural network to identify spoken dialogue information based on visual content, such as artificial visual representations and spoken dialogue indications. The transcription data is then updated based on the identified spoken dialogue information associated with each speech segment. This innovative method allows for a detailed analysis of conversation participants' talk times, ratios, longest monologues, interactivity, and other parameters, providing valuable insights for users.
To know more about GlobalData’s detailed insights on Gong I.O, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
