Voice-Controlled Call Requests With Server-Side Speech Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech recognition and natural language understanding systems are computationally expensive and require significant resources, making it challenging to efficiently process speech-based commands in a distributed computing environment, especially for input-limited devices like speech-controlled devices.
Innovation Solution
A system that utilizes a distributed computing environment to process speech commands, where local devices capture audio signals, convert them into text, and send it to remote servers for further processing, enabling communication establishment between speech-controlled devices by previewing the call details to the recipient before connection, allowing acceptance or rejection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech recognition and natural language understanding processing are performed locally on input-limited devices, then user interaction capability is improved, but device complexity and computational resource requirements increase
Solution Approach 1:
The system divides speech processing into two segments: local device performs audio capture and initial speech-to-text conversion, while remote server performs natural language understanding and command execution. This segmentation reduces the computational burden on input-limited devices while maintaining sophisticated user interaction capabilities.
Solution Approach 2:
A remote server acts as an intermediary that receives simplified text data from local devices, performs complex natural language understanding processing, and returns appropriate commands or responses. This intermediary approach allows sophisticated processing without requiring local devices to have substantial computational resources.
2Productivity
If distributed computing environment is used for speech processing, then computational efficiency is improved, but system complexity and communication overhead increase
Solution Approach 1:
The patent extracts the complex natural language understanding and command interpretation functions from local devices and places them on remote servers. Only the essential audio capture and text conversion remain locally, significantly simplifying the overall system architecture while maintaining computational efficiency through distributed processing.
3Speed
If speech commands are processed in real-time, then user interaction responsiveness is improved, but computational resource consumption increases
Solution Approach 1:
The system performs partial speech processing actions locally (audio capture, basic speech-to-text conversion) to maintain real-time responsiveness, while deferring computationally intensive natural language understanding to remote servers. This partial action approach ensures fast user interaction while reducing overall computational resource consumption on energy-constrained devices.
Data Source
AI summary
Systems and methods for establishing communication connections using speech, such as establishing calls between devices, are described. A first device receives a communication request in the form of audio and sends audio data corresponding to the captured audio to a server. The server determines a recipient, a subject for the call, and a device associated with the recipient. The server then sends a message indicating the communication request and audio data corresponding to the communication topic to the recipient's speech-controlled device. The recipient device outputs audio to the recipient requesting whether the recipient accepts the communication request. The recipient audibly refuses or accepts the communication request, and the recipient's speech-controlled device sends an indication of the recipient's audible decision to the server. If the recipient accepted the communication request, the server causes a communication connection to be established between the two speech-controlled devices.