Media Gateway Speech Recognition and Enrolment Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing media gateways (MG) in next-generation networks (NGN) architectures are unable to implement speech recognition and enrolment independently, requiring control from the media gateway controller (MGC) to facilitate these processes.
Innovation Solution
A method and apparatus where the MG receives a Speech Enrolment Start Request and a Speech Recognition Request from the MGC, performs speech recognition and enrolment, and feeds back the results to the MGC, enabling the MG to independently handle speech recognition and enrolment under the MGC's control through extended H.248 signals and protocol headers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the MG is separated from the MGC in NGN architecture, then network flexibility and scalability are improved, but the MG loses the capability to perform speech recognition and enrolment independently
Solution Approach 1:
The MG is enhanced with self-service capabilities to perform speech recognition and enrolment independently without requiring the MGC. The MG includes a speech recognition module that can autonomously recognize user identity through speech signals and an enrolment module that can independently enrol new users by capturing and processing their speech samples, eliminating the functional deficiency caused by separation from MGC.
Solution Approach 2:
The MG is designed with multi-functionality, combining traditional media gateway functions (call setup, resource management) with speech recognition and enrolment capabilities. This universal design allows the MG to handle both conventional telephony operations and speech-based services within a single device, improving network flexibility while maintaining complete speech recognition functionality.
2Adaptability or versatility
If the MG performs speech recognition independently, then service capability is improved, but device complexity increases
Solution Approach 1:
The speech recognition functionality is segmented into a separate speech recognition module within the MG, distinct from the core media gateway functions. This modular segmentation allows the speech recognition capability to be added without fundamentally redesigning the entire MG architecture, thereby improving service capability while managing device complexity through organized functional separation.
Solution Approach 2:
An intermediary interface layer is introduced between the speech recognition module and the core MG functions. This intermediary handles the coordination and data exchange between speech processing and media gateway operations, allowing the speech recognition functionality to be integrated without creating complex direct couplings between components, thus managing overall system complexity.
Data Source
AI summary
A method and an apparatus for performing and controlling speech recognition and enrolment are provided. The method for performing speech recognition and enrolment includes: receiving a Speech Enrolment Start Request and a Speech Recognition Request sent from a media gateway controller (MGC); performing speech recognition and enrolment according to the Speech Enrolment Start Request and the Speech Recognition Request, and obtaining a recognition and enrolment result; and feeding back the recognition and enrolment result to the MGC.