Progressive Audio Query Matching for Latency Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Music recognition programs experience significant latency due to the time it takes for users to initiate audio capture and query processing, leading to an undesirable user experience as information retrieval from servers takes 12 seconds or longer.
Innovation Solution
Implementing a system where a device captures audio data from a background environment and processes it to formulate progressive queries transmitted to a content recognition service, employing a multi-stage matching technique to reduce latency and increase query throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional audio capture and query processing is used, then content recognition can be performed, but latency increases to 12 seconds or longer
Solution Approach 1:
The system performs preliminary actions by capturing audio data from the background environment continuously before the user initiates the recognition task. This pre-captured audio data is then used to formulate queries, eliminating the need to wait for audio capture during the actual recognition process, thereby reducing latency from 12+ seconds to under 1 second.
Solution Approach 2:
The query formulation process is segmented into multiple progressive queries that incorporate previous queries plus additional data. This segmentation allows the system to process queries in smaller, manageable increments rather than waiting for a complete audio capture sequence, significantly reducing the time to return results.
2Productivity
If multiple queries are transmitted progressively, then query throughput increases, but query complexity increases
Solution Approach 1:
The query process is divided into multiple progressive queries, each incorporating previous queries plus additional data. This segmentation enables the system to transmit multiple queries progressively, increasing throughput while managing complexity through incremental data addition rather than handling a single complex query.
Solution Approach 2:
The system uses feedback from previous queries to formulate subsequent queries. Each progressive query incorporates the results and data from previous queries, allowing the system to build upon prior information and reduce the complexity of individual queries while maintaining high throughput through parallel processing.
Data Source
AI summary
Various embodiments enable audio data, such as music data, to be captured, by a device, from a background environment and processed to formulate a query that can then be transmitted to a content recognition service. In one or more embodiments, multiple queries are transmitted to the content recognition service. In at least some embodiments, subsequent queries can progressively incorporate previous queries plus additional data that is captured. In one or more embodiments, responsive to receiving the query, the content recognition service can employ a multi-stage matching technique to identify content items responding to the query. This matching technique can be employed as queries are progressively received.