Wearable terminal
A wearable, terminal technology, applied in TV, voice analysis, communication between multiple stations, etc., can solve the problem of narrow profile performance range, etc., to achieve the effect of widening the performance range
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach 1
[0102]
[0103] First, an outline of a wearable terminal according to the present invention will be described.
[0104] In the present invention, as figure 1 As shown, the user wears the wearable terminal 100, such as figure 2 As shown, it is assumed that a user wearing a wearable terminal has a plurality of people nearby. There are multiple users as the above-mentioned users, and various situations such as meetings, lectures, meals, standing chats, group trips, and parties can be considered. Here, it is considered that there is a group (conversation group) having a conversation among a plurality of users existing nearby. Of course, there may be a plurality of such conversation groups, and there may be persons who do not participate in the conversation. In addition, the conversation mentioned here is not a case where one person continues to speak for a long time (for example, more than 1 minute), but a case where speakers are appropriately exchanged.
[0105] Such as ...
Embodiment approach 2
[0172] In Embodiment 1, a configuration was described in which wearable terminal 100 detects a wearable terminal that provides an image required for profiling, acquires an image from the detected wearable terminal, and realizes profiling using the acquired image. production (P2P-type ad-hoc (ad hoc group wireless network) mode).
[0173] On the other hand, in this embodiment mode, the following structure will be described, that is, as Figure 21 As shown, the production server that collectively manages and controls multiple wearable terminals efficiently determines conversation groups (conversation groups 1 to k) that share images and sounds, and uses the images and sounds acquired by the wearable terminals belonging to each conversation group. , create a profile for each conversation group, and transmit the created profile to wearable terminals belonging to each conversation group through communication (server mode of centralized server management).
[0174] Describes the ...
Embodiment approach 3
[0201] In Embodiments 1 and 2, wearable terminals belonging to the same conversation group were detected based on the degree of overlap of utterance segments. However, in this embodiment, it is possible to detect echoes and Use it in the same session group detection process. This embodiment describes the case where append is used in the same conversation group detection process. The consonance referred to here refers to words containing long vowel sounds such as "hey~", "oh~" and "um~". Echoing is mostly such a long vowel sound, and is mostly a polite remark in itself. Therefore, for example, vowel detection is performed using parameters representing numerical values characteristic of vowels, such as cepstrum or LPC coefficient, and consonance detection can be easily performed based on a condition judgment method such that the duration is, for example, 200 msec or more and 2 sec or less. Of course, the attachment detection method is not limited to the methods listed here. ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com