Voice Input Completion Suggestions to Reduce Assistant Dialog Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated assistants often fail to comprehend incomplete or improperly formatted spoken utterances, leading to resource wastage and latency in performing intended actions, as they process and respond with errors or require reformulation of the utterance.
Innovation Solution
Provide real-time suggestions via a display modality to complete spoken utterances, guiding users to formulate actionable requests by combining initial inputs with suggested text or graphical elements, and optionally biasing speech-to-text processing to enhance accuracy and reduce interaction time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the automated assistant processes spoken utterances without providing completion suggestions, then the user can freely formulate requests, but the assistant consumes computational resources on incomplete or erroneous inputs and experiences latency before performing the intended action
Solution Approach 1:
The system performs preliminary action by analyzing the spoken utterance in real-time and generating completion suggestions before the user finishes speaking or before the assistant would normally process the incomplete input. This allows the assistant to prepare appropriate responses and guide the user toward completing the request, thereby reducing the time lost to processing incomplete or erroneous inputs and eliminating the need for repeated utterances.
2Reliability
If the automated assistant processes incomplete spoken utterances, then it can attempt to understand user intent, but it wastes computational and network resources on inputs that cannot be fully processed
Solution Approach 1:
The system implements feedback by providing real-time completion suggestions to the user based on the incomplete spoken utterance. This feedback mechanism guides the user in formulating complete and accurate requests, thereby improving request processing accuracy. Simultaneously, by preventing the processing of incomplete or erroneous inputs through proactive guidance, the system reduces wasteful consumption of computational and network resources.
3Manufacturing precision
If the automated assistant requires users to reformulate spoken utterances, then it can ensure proper syntax and completeness, but it increases interaction time and creates a less efficient user experience
Solution Approach 1:
The system enables self-service by providing automated completion suggestions that help users formulate correct utterances without requiring them to actively correct their own mistakes or reformulate their requests. The assistant analyzes the incomplete input and generates appropriate completions, allowing users to simply confirm or make minimal adjustments. This approach ensures proper syntax and completeness while maintaining high interaction efficiency, as users do not need to spend time reformulating their requests.
Data Source
Figure 1A
Figure 1B
Figure 2A
AI summary
Implementations described herein relate to providing suggestions, via a display modality, for completing a spoken utterance for an automated assistant, in order to reduce a frequency and/or a length of time that the user will participate in a current and/or subsequent dialog session with the automated assistant. A user request can be compiled from content of an ongoing spoken utterance and content of any selected suggestion elements. When a currently compiled portion of the user request (from content of a selected suggestion(s) and an incomplete spoken utterance) is capable of being performed via the automated assistant, any actions corresponding to the currently compiled portion of the user request can be performed via the automated assistant. Furthermore, any further content resulting from performance of the actions, along with any discernible context, can be used for providing further suggestions.