Samsung electronics co., ltd. (20240127805). ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF simplified abstract
ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF
Organization Name
Inventor(s)
Dhairya Sandhyana of Suwon-si (KR)
ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240127805 titled 'ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF
Simplified Explanation
The electronic apparatus described in the abstract is designed to receive image and speech data, extract objects and characters from the image data, identify object names and characters, generate bias keyword lists based on the identified objects and characters, convert speech data to text using the bias keyword lists and a language contextual model, and display the converted text as captions.
- Communication interface to receive content with image and speech data
- Memory to store a language contextual model trained with relevance between words
- Display for showing the converted text
- Processor to extract objects and characters, identify object names, generate bias keyword lists, convert speech data to text, and control display
Potential Applications
This technology can be used in various applications such as:
- Automatic captioning for images and videos
- Language translation for speech data
- Content indexing and search optimization
Problems Solved
This technology addresses the following issues:
- Improving accessibility for individuals with hearing impairments
- Enhancing user experience by providing contextual information
- Streamlining content creation and management processes
Benefits
The benefits of this technology include:
- Increased efficiency in content processing and delivery
- Enhanced user engagement through multimedia content
- Improved accuracy in speech-to-text conversion
Potential Commercial Applications
The potential commercial applications of this technology include:
- Media and entertainment industry for captioning and subtitling
- E-learning platforms for language translation and transcription services
- Marketing and advertising agencies for content optimization and personalization
Possible Prior Art
One possible prior art for this technology could be existing speech recognition and image processing systems that are used for similar purposes. These systems may not have the same level of integration and contextual understanding as the described electronic apparatus.
Unanswered Questions
How does the language contextual model improve the accuracy of speech-to-text conversion?
The language contextual model stores information about the relevance between words, helping the processor to better understand the context of the speech data and generate more accurate text output.
What is the impact of using bias keyword lists on the conversion process?
The bias keyword lists help the processor to focus on specific image-related words associated with the objects and characters in the image data, improving the relevance and accuracy of the converted text.
Original Abstract Submitted
an electronic apparatus and a control method thereof are provided. the electronic apparatus includes a communication interface configured to receive content comprising image data and speech data; a memory configured to store a language contextual model trained with relevance between words; a display; and a processor configured to: extract an object and a character included in the image data, identify an object name of the object and the character, generate a bias keyword list comprising an image-related word that is associated with the image data, based on the identified object name and the identified character, convert the speech data to a text based on the bias keyword list and the language contextual model, and control the display to display the text that is converted from the speech data, as a caption.
(Ad) Transform your business with AI in minutes, not months
Trusted by 1,000+ companies worldwide
