Voice Dialing Model Selection via Context Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice recognition systems in electronic devices, such as phones and head units, are limited to recognizing voices in specific languages like Chinese, English, and Japanese, and fail to support dialects or other languages, restricting their functionality in multilingual environments.
Innovation Solution
The system determines possible languages used in voice dialing based on collected information, such as phonebook content, operating system language, and historical position data, and dynamically downloads or requests appropriate acoustic and language models from voice recognition engines to match user voice inputs with contact names in the phonebook, enabling recognition and dialing across multiple languages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the electronic device pre-stores acoustic models and language models for specific languages (Chinese, English, Japanese), then voice recognition accuracy for these languages is improved, but the system's ability to recognize dialects and other languages deteriorates
Solution Approach 1:
The system dynamically determines the language to be used for voice recognition based on collected information such as phonebook content, operating system language, and historical position data. Instead of being static with pre-defined language support, the system adapts its language model selection in real-time based on user context and location, enabling recognition of dialects and languages not previously hard-coded.
Solution Approach 2:
The electronic device automatically collects information from its own resources (phonebook, operating system settings, location history) to determine the appropriate language for voice recognition without requiring manual configuration. The system serves itself by autonomously selecting and loading the correct acoustic and language models based on collected data, eliminating the need for users to manually select languages or configure recognition parameters.
2Adaptability or versatility
If the system supports multiple languages by pre-loading multiple acoustic models and language models, then language versatility is improved, but device complexity and memory requirements deteriorate
Solution Approach 1:
The voice recognition system is segmented into modular components: an information collection module that gathers data from various sources, a language determination module that processes this data to identify the target language, and a model loading module that retrieves the corresponding acoustic and language models. This segmentation allows the system to handle multiple languages through a structured, manageable process rather than requiring all models to be loaded simultaneously.
Solution Approach 2:
The system performs preliminary actions by collecting relevant information (phonebook content, OS language, location history) before the actual voice recognition occurs. Based on this pre-collected data, the system determines the appropriate language and loads the corresponding models in advance, ensuring that the correct models are ready for recognition without requiring the device to maintain multiple models in memory simultaneously.
3Measurement precision
If the electronic device collects and processes information from multiple sources to determine language, then language determination accuracy is improved, but processing time and computational resources deteriorate
Solution Approach 1:
The system collects information from multiple sources (phonebook content, operating system language, historical position data) to determine the target language. By gathering more information than strictly necessary, the system improves the accuracy of language determination, especially in cases where the user's primary language may not be immediately obvious from a single data source. The additional information acts as a backup or confirmation mechanism.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A voice recognition-based dialing method and a voice recognition-based dialing system are provided. The methods includes: determining a recognition result based on a user's voice input, at least one acoustic model and at least one language model, where the at least one acoustic model and the at least one language model are obtained based on information collected in an electronic device. The system includes: obtain at least one acoustic model and at least one language model based on information collected in an electronic device; and determine a recognition result based on a user's voice input, the at least one acoustic model and the at least one language model. The acoustic models and the language models are updated based on the information collected in the electronic device, which may be helpful to the voice recognition-based dialing.