Speaker-Independent Speech Indexing for Multi-Language File Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current speech-activated devices require pre-programming for voice input association, are limited by English language dominance, and lack multi-language recognition capabilities, making them inconvenient and costly to manufacture for diverse markets.
Innovation Solution
A method and apparatus that generate an index of digital file information entries, receive speaker-independent speech input in multiple languages, determine the input language, and compare it with the index to access digital files, allowing for seamless access without pre-recording and accommodating various character code sets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pre-programming is used to associate voice input with particular entries, then speech recognition accuracy is improved, but device complexity and ease of operation deteriorate due to tedious setup process
Solution Approach 1:
The system performs preliminary indexing of all digital files during initialization, creating a searchable database of file information including names, metadata, and content keywords. This preliminary action eliminates the need for users to pre-program voice associations, as the system is already prepared to recognize and match speech inputs against the indexed data.
Solution Approach 2:
The system automatically indexes digital files and manages the speech recognition database without requiring user intervention. The device serves itself by continuously maintaining an updated index of files, allowing users to simply speak their requests without any setup or programming effort.
2Adaptability or versatility
If multiple language recognition capabilities are added, then adaptability is improved, but manufacturing cost increases due to dedicated production lines
Solution Approach 1:
The system uses a universal speech recognition engine that can handle multiple languages through software configuration rather than hardware differentiation. The same device firmware and hardware platform support multiple languages, eliminating the need for dedicated production lines for each language version.
Solution Approach 2:
The system changes the language parameter dynamically based on user input or system detection. By modifying software parameters (language models, character encodings) rather than hardware configuration, the same device can adapt to different languages without requiring different manufacturing processes.
3Adaptability or versatility
If character code set management is improved for multiple languages, then adaptability is improved, but device complexity increases
Solution Approach 1:
The system introduces an intermediary layer (software abstraction layer) that handles character code set conversions between different encodings (ASCII, Big-5, GB, JIS, etc.). This intermediary manages the complexity of multiple code sets internally, presenting a unified interface to users while handling encoding conversions transparently.
Data Source
AI summary
There is provided a method for accessing at least one digital file from a collection comprising more than one digital file in an electronic device, including: generating one index comprising of information entries obtained from each of the more than one digital file in the collection, with each digital file in the collection information being linked to at least one information entry; receiving a speaker independent speech input in at least one language during a speech reception mode; determining a language of the speech input; and setting the speech reception mode to the language of the speech input; comparing the speech input received during the speech reception mode with the entries in the index. The file may advantageously be accessed when the speech input coincides with at least one of the information entries in the index. The digital files may be stored in the electronic device, any device functionally connected to the electronic device or a combination of the aforementioned. The at least one digital file may be received from a source selected from: a memory device, a wired computer network or a wireless computer network. An apparatus that is able to carry out the aforementioned method is also disclosed.