18083251. SPEECH RECOGNITION METHOD AND APPARATUS simplified abstract (Samsung Electronics Co., Ltd.)
Contents
SPEECH RECOGNITION METHOD AND APPARATUS
Organization Name
Inventor(s)
SPEECH RECOGNITION METHOD AND APPARATUS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18083251 titled 'SPEECH RECOGNITION METHOD AND APPARATUS
Simplified Explanation
The patent application describes a method for speech recognition that involves replacing phonetic symbol sequences with corresponding words to determine the target text of a speech.
- The method receives speech data and extracts a candidate text with a phonetic symbol sequence associated with a target word.
- A speech recognition model is used to replace the phonetic symbol sequence with a replacement word.
- The target text is determined based on the result of the replacement.
Potential Applications
- Speech recognition systems and software
- Voice assistants and virtual agents
- Transcription services
- Language learning tools
Problems Solved
- Improves accuracy and efficiency of speech recognition
- Enhances the understanding of spoken language
- Reduces errors in transcribing speech
Benefits
- More accurate and reliable speech recognition
- Improved user experience with voice-controlled devices
- Increased productivity in transcription services
- Enhanced language learning tools
Original Abstract Submitted
A speech recognition method includes receiving speech data, obtaining, from the received speech data, a candidate text including at least one word and a phonetic symbol sequence associated with a pronunciation of a target word included in the received speech data, using a speech recognition model, replacing the phonetic symbol sequence included in the candidate text with a replacement word corresponding to the phonetic symbol sequence, and determining a target text corresponding to the received speech data based on a result of the replacing.