Hybrid Text Input System Combining Keypad and Speech Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional text input methods in portable devices are inconvenient due to the need for direct letter-by-letter input and have low speech recognition rates, making it difficult to input text quickly and naturally, especially in devices like mobile terminals and digital TVs.
Innovation Solution
A method and apparatus that automatically complete text input by receiving a first part of the text from a user through a text input device, recognizing the corresponding speech, and completing the remaining text based on the input and recognized speech, allowing simultaneous text input and speech recognition without strict timing order.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If direct input method using keypad or keyboard is used, then text can be input exactly, but it takes a lot of time and is inconvenient due to letter-by-letter input
Solution Approach 1:
The patent combines direct text input method and speech recognition method into a hybrid system. The user can input some text directly via keyboard and speak the remaining portion, allowing the system to merge both input modes and complete the text automatically, thus improving input speed while maintaining accuracy.
Solution Approach 2:
The system performs preliminary speech recognition on the spoken portion before final text completion. By recognizing speech in advance and preparing the corresponding text, the system reduces the time needed for final text input and improves overall text input efficiency.
2Ease of operation
If speech recognition method is used, then text can be input without direct typing, but recognition rate is low and requires repeated correction
Solution Approach 1:
The patent introduces a text completion system as an intermediary between speech recognition and final text output. The system uses the recognized speech to generate candidate completions and combines them with directly typed text, providing a mediation layer that improves recognition reliability by allowing user verification and correction.
Solution Approach 2:
The system provides feedback to the user by displaying the combined text (typed + speech-recognized) for verification. This feedback mechanism allows users to review and correct recognition errors, thereby improving the overall reliability of the text input process.
3Extent of automation
If speech recognition is performed first, then recognized speech must be identified or recognized again, making input operation and speech recognition separate
Solution Approach 1:
The patent merges speech recognition and text input operations into a unified process. Instead of performing speech recognition first and then separately identifying the text, the system simultaneously processes both spoken and typed input, combining them into a single text completion operation that feels more natural to users.
Data Source
AI summary
Provided are a method and apparatus for automatically completing a text input using speech recognition. The method includes: receiving a first part of a text from a user through a text input device; recognizing a speech of the user, which corresponds to the text; and completing a remaining part of the text based on the first part of the text and the recognized speech. Therefore, accuracy of the text input and convenience of the speech recognition can be ensured, and a non-input part of the text can be easily input based on the input part of the text and the recognized speech at a high speed.