Digital Audio Signal Identification via Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately and reliably recognizing digital audio signals across various configurations and implementations, particularly due to differences in digital transmission standards and the incompatibility of analog audio codes with digital compression.
Innovation Solution
A digital signal recognition system that processes digital audio signals through an SP/DIF connection, capable of reading identifying labels from both compressed and decompressed signals, and extracting signatures, which are then stored and forwarded to a central facility for identification, using techniques such as reading labels from auxiliary data fields and extracting checksums from frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If analog audio codes are used for signal identification, then the system works well with analog video signals, but the codes do not survive data compression in digital transmission
Solution Approach 1:
The patent changes the identification approach from using analog-style embedded codes to using digital audio signal characteristics (spectral features, temporal patterns, statistical properties) that can be extracted and compared without requiring the original code structure to survive compression. This parameter change allows identification to work reliably across different digital transmission standards and compression algorithms.
Solution Approach 2:
The patent replaces the mechanical approach of embedding identifiable codes in the audio signal with a computational approach that extracts characteristic features from the compressed digital audio signal. Instead of relying on physical code presence, the system uses digital signal processing to identify programs through feature comparison, which is compatible with all digital compression standards.
2Adaptability or versatility
If multiple digital transmission standards are supported, then the system becomes more versatile, but the complexity of handling various standards increases
Solution Approach 1:
The patent creates a universal identification system that works across multiple digital transmission standards (ATSC, DVB, ISDB) by using standard digital audio signal processing techniques. The system extracts characteristic features from the digital audio signal that are independent of the specific transmission standard, allowing one system to handle multiple standards without requiring standard-specific processing modules.
Solution Approach 2:
The patent changes from standard-specific code recognition to standard-agnostic feature extraction. By using spectral features, temporal patterns, and statistical properties of digital audio signals, the system achieves versatility across multiple transmission standards while maintaining relatively simple processing complexity, as these features can be extracted using通用 digital signal processing methods.
3Measurement precision
If identifying labels are extracted from compressed digital audio signals, then identification accuracy improves, but the processing time and computational resources increase
Solution Approach 1:
The patent extracts only the essential characteristic features from the digital audio signal that are sufficient for identification, rather than processing the entire signal. By selecting key spectral features, temporal patterns, and statistical properties, the system achieves high identification accuracy while minimizing processing time and computational resource requirements.
Solution Approach 2:
The patent applies partial action by extracting a limited set of characteristic features from the digital audio signal that provide sufficient identification accuracy. Instead of analyzing all aspects of the signal, the system focuses on the most discriminative features, achieving good measurement precision with reduced processing time and computational overhead.
Data Source
AI summary
Method and apparatus for identifying broadcast digital audio signals include structure and/or function whereby the digital audio signal is provided to processing structure which is configured to (i) identify a program-identifying code in the received digital audio signal, (ii) identify a program-identifying code in a decompressed received digital audio signal, (iii) identify a feature signature in the received digital audio signal, and (iv) identify a feature signature in the decompressed received digital audio signal. Preferably, such processing structure is disposed in a dwelling or a monitoring site in an audience measurement system, such as the Nielsen TV ratings system.