Speech Processing Apparatus Incomplete Utterance Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing speech processing systems cannot determine which electronic device to operate when a voice command from a user can be processed by multiple devices, and they fail to complete incomplete spoken utterances, leading to inefficient speech recognition and user dissatisfaction.
Innovation Solution
A speech processing method that converts spoken utterances into text, performs syntactic and semantic analysis to identify domains and intents, generates query utterances to fill missing slots, and receives user responses to complete the utterance, thereby determining and operating the appropriate device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If speech processing systems process voice commands that can be executed by multiple electronic devices, then the system can handle more versatile commands, but it cannot determine which specific device to operate
Solution Approach 1:
The system feeds back a spoken query utterance to the user asking for clarification about which device to operate. The user's response provides the missing device identification information, allowing the system to complete the incomplete spoken utterance and execute the command on the correct device.
Solution Approach 2:
The system performs syntactic and semantic analysis on the spoken utterance before execution to identify incomplete information. When a command can be processed by multiple devices, the system proactively generates and outputs a query to obtain the necessary device identification before proceeding with command execution.
2Measurement precision
If the system requests clarification for incomplete utterances, then speech recognition accuracy improves, but user interaction time increases
Solution Approach 1:
The system performs partial analysis (syntactic and semantic analysis) on the spoken utterance to identify incomplete information without requiring full re-phrasing from the user. This partial processing approach maintains high recognition accuracy while minimizing additional interaction time by only requesting the specific missing information.
3Manufacturing precision
If the system analyzes spoken utterances to identify incomplete information, then command execution accuracy improves, but processing complexity increases
Solution Approach 1:
The command processing system is segmented into distinct functional modules: speech recognition module, syntactic analysis module, semantic analysis module, and command execution module. This segmentation allows each module to perform its specific function independently, improving overall execution accuracy while making the complex processing system more manageable and maintainable.
Data Source
AI summary
Disclosed are a speech processing method and speech processing apparatus which execute an installed artificial intelligence (AI) algorithm and/or machine learning algorithm to perform speech processing to enable the speech processing apparatus, a user terminal, and a server to communicate with each other in a 5G communication environment. The speech processing method according to an exemplary embodiment of the present disclosure includes converting a user's spoken utterance into a user utterance text, discovering a domain, an intent, and at least one named entity of the user utterance text, determining whether the user's spoken utterance is a complete spoken utterance or an incomplete spoken utterance, generating a spoken query utterance and feeding the generated spoken query utterance back to the user when the user's spoken utterance is an incomplete spoken utterance, and constructing a complete spoken utterance by receiving a user's spoken response utterance which responds to the spoken query utterance.