Microsoft Technology Licensing, LLC (20240273139). SUGGESTED QUERIES FOR TRANSCRIPT SEARCH simplified abstract
Contents
SUGGESTED QUERIES FOR TRANSCRIPT SEARCH
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Adi Miller of Ramat Hasharon (IL)
Michael Sterenberg of Herzliya (IL)
SUGGESTED QUERIES FOR TRANSCRIPT SEARCH - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240273139 titled 'SUGGESTED QUERIES FOR TRANSCRIPT SEARCH
The abstract describes systems and methods for surfacing natural language queries from one or more transcripts. This involves converting audio to text, generating input signals based on the transcript, and using heuristics or machine learning models to suggest natural language queries for searching the transcript or key moments within the audio.
- Automated speech recognition is used to convert received audio to text.
- The transcript includes text of the audio and identifications of speakers associated with portions of the text.
- Input signals are generated based on the transcript.
- Heuristics or machine learning models are executed to suggest natural language queries for searching the transcript or key moments within the audio.
- The suggested queries or key moments are surfaced on remote devices.
Potential Applications: - Enhancing search capabilities for audio content - Improving accessibility for individuals with hearing impairments - Streamlining content indexing and retrieval processes
Problems Solved: - Facilitating efficient search and retrieval of information from audio content - Enhancing user experience by providing relevant search suggestions - Addressing the challenge of identifying key moments within lengthy audio recordings
Benefits: - Increased efficiency in searching and retrieving information from audio content - Enhanced accessibility for individuals with hearing impairments - Improved user experience through personalized search suggestions
Commercial Applications: Title: Enhanced Audio Search and Retrieval Technology This technology can be utilized in various industries such as: - Media and entertainment for content indexing and search optimization - Education for enhancing accessibility to audio resources - Customer service for analyzing and retrieving information from call recordings
Questions about the technology: 1. How does this technology improve the search experience for users? 2. What are the potential implications of this technology for content creators and distributors?
Original Abstract Submitted
systems and methods for surfacing natural language queries from one or more transcripts. an example method may include converting received audio to text, through automated speech recognition, to form a transcript of the audio, wherein the transcript includes text of the audio and identifications of speakers associated with portions of the text corresponding to utterances from the respective speakers; generating input signals based on at least the transcript; executing at least one of one or more heuristics or a trained machine-learning (ml) model, using the generated input signals as an input, to generate at least one of a suggested natural language query for searching the transcript or a key moment within the received audio; and causing at least one of the suggested natural language query or the key moment to be surfaced on one or more remote devices.
