Google llc (20240296835). BACKGROUND AUDIO IDENTIFICATION FOR SPEECH DISAMBIGUATION simplified abstract
Contents
BACKGROUND AUDIO IDENTIFICATION FOR SPEECH DISAMBIGUATION
Organization Name
Inventor(s)
Jason Sanders of New York NY (US)
Gabriel Taubman of Brooklyn NY (US)
John J. Lee of Long Island City NY (US)
BACKGROUND AUDIO IDENTIFICATION FOR SPEECH DISAMBIGUATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240296835 titled 'BACKGROUND AUDIO IDENTIFICATION FOR SPEECH DISAMBIGUATION
The patent application describes a method for providing context-dependent search results based on audio streams received by a computing device.
- The method involves separating the audio stream into user speech data and background audio, identifying concepts related to the background audio, and generating terms related to these concepts.
- The speech recognizer is influenced by these terms related to the background audio to improve the recognition of user speech data.
- The recognized version of the user speech data is obtained using the speech recognizer.
Potential Applications: - This technology could be used in voice-controlled search engines to provide more accurate results based on the context of the background audio. - It could also be applied in virtual assistants to enhance their understanding of user commands in noisy environments.
Problems Solved: - This technology addresses the challenge of accurately recognizing user speech data in the presence of background audio. - It helps improve the relevance of search results by considering the context in which the user speech data is captured.
Benefits: - Enhanced accuracy in speech recognition in noisy environments. - Improved user experience with voice-controlled devices. - More relevant search results based on the context of the audio environment.
Commercial Applications: - This technology could be valuable for companies developing voice-controlled devices, virtual assistants, and search engines. - It has the potential to improve the performance and user satisfaction of products that rely on speech recognition technology.
Questions about the technology: 1. How does this method improve the accuracy of speech recognition in noisy environments? 2. What are the potential implications of using background audio to influence speech recognition in various applications?
Original Abstract Submitted
implementations relate to techniques for providing context-dependent search results. a computer-implemented method includes receiving an audio stream at a computing device during a time interval, the audio stream comprising user speech data and background audio, separating the audio stream into a first substream that includes the user speech data and a second substream that includes the background audio, identifying concepts related to the background audio, generating a set of terms related to the identified concepts, influencing a speech recognizer based on at least one of the terms related to the background audio, and obtaining a recognized version of the user speech data using the speech recognizer.
