Automated Voice Enablement for Web Free Form Input Fields
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The widespread adoption of voice-enabled Web applications is hindered by the complexity of integrating speech processing with Web pages, requiring expertise in both Web and speech application development, and the need for different grammars for varying fields, which many businesses lack the resources to coordinate.
Innovation Solution
A method for automated voice enablement of Web pages with free form input field support, where a core attribute specifies permitted terms or references an external statistical language model, allowing speech input to be processed by an ASR engine and seamlessly integrated into the Web page without requiring speech recognition expertise, supporting both closed and free form input fields.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If different grammars are generated for each field to support varying input requirements, then speech recognition accuracy is improved, but device complexity and development cost increase
Solution Approach 1:
The system automatically generates speech grammars by extracting permitted terms from HTML form field attributes (such as 'permitted-terms' or 'core-attribute') without requiring manual grammar configuration. The speech recognition engine self-configures by reading the form field definitions, eliminating the need for separate grammar authoring processes for each field.
Solution Approach 2:
An intermediary layer is introduced between the HTML form definition and the speech recognition grammar. The system extracts permitted terms from the form field attributes as an intermediate representation, then automatically converts this into the appropriate speech grammar format, decoupling the form design from the speech recognition configuration.
2Adaptability or versatility
If speech processing is integrated with Web pages requiring coordination between speech developer and Web developer, then voice enabled application functionality is improved, but ease of manufacture decreases
Solution Approach 1:
The speech grammar generation capability is extracted from the speech recognition engine and implemented as a standalone automated process that reads form field attributes. This extraction allows the system to handle voice-enabled Web forms independently without requiring close coordination between speech developers and Web developers, as the grammar generation is automated based on the form structure.
Solution Approach 2:
The system provides universal support for various input field types (text, email, phone, date, etc.) through a single automated grammar generation mechanism. The same process handles different field types by extracting their specific permitted terms from the form attributes, eliminating the need for separate integration approaches for each field type.
3Measurement precision
If manual grammar generation is performed for each field, then speech recognition precision is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary extraction of permitted terms from the form field attributes during the Web page generation process. By preparing the grammar data in advance from the form definitions, the system eliminates the need for manual grammar generation during or after development, significantly reducing the time required for speech recognition setup.
Data Source
AI summary
Embodiments of the present invention provide a method and computer program product for the automated voice enablement of a Web page with free form input field support. In an embodiment of the invention, a method for voice enabling a Web page with free form input field support can be provided. The method can include receiving speech input for an input field in a Web page, parsing a core attribute for the input field and identifying an external statistical language model (SLM) referenced by the core attribute of the input field, posting the received speech input and the SLM to an automatic speech recognition (ASR) engine, and inserting a textual equivalent to the speech input provided by the ASR engine in conjunction with the SLM into the input field.