Sound source localization method and device, localization device and storage medium
A sound source localization and sound source technology, applied in the information field, can solve problems such as insufficient sound source accuracy, and achieve the effects of improving user experience, reducing misoperation, and precise control
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0137] This example provides a sound source localization device capable of implementing the aforementioned sound source localization method. For details, please refer to Figure 6 shown, including:
[0138] Audio collector: record the user's audio corpus through the microphone in the car, at least 2 microphones.
[0139] Voiceprint feature extraction model: Based on voiceprint recognition technology, collect the wake-up word audio files spoken by users, and classify different users through audio feature extraction (such as MFCC feature extraction algorithm).
[0140] Usually wake words are used for voiceprint recognition. The audio collector here is the aforementioned first collection module and / or the second collection module.
[0141] Sound source localization classifier: For a certain time range, the certain time range can suggest 1 day or half a day, 2 hours or 1 hour, etc., and count the frequency probability of the location source of each corpus spoken by the classifie...
example 2
[0150] Such as Figure 7 As shown, this example provides a sound source localization method, including:
[0151] voice recording;
[0152] Extract voiceprint features to identify user identity;
[0153] For the first authentication, set the preferred location information as the main driver;
[0154] Sound source localization obtains the angle θ of the sound source;
[0155] Determine if the angle θ is close to the median value of 90°,
[0156] If so, there is an error in the recognition angle θ;
[0157] If not, the recognition angle θ is reasonable;
[0158] If there is an error, determine whether there is only one person on the left of the main driver and the co-driver;
[0159] If there is only one person, obtain the location of the user, and directly determine the sound source based on the single user on the main driver or the co-driver;
[0160] If there is not only one person, use the search classifier to obtain the user's preferred position, and combine the prefe...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More - R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com



