20240022224. AUTOMATIC GENERATION AND SELECTION OF TARGET PROFILES FOR DYNAMIC EQUALIZATION OF AUDIO CONTENT simplified abstract (DOLBY LABORATORIES LICENSING CORPORATION)
Contents
AUTOMATIC GENERATION AND SELECTION OF TARGET PROFILES FOR DYNAMIC EQUALIZATION OF AUDIO CONTENT
Organization Name
DOLBY LABORATORIES LICENSING CORPORATION
Inventor(s)
Giulio Cengarle of Barcelona (ES)
Nicholas Laurence Engel of San Francisco CA (US)
Patrick Winfrey Scannell of San Francisco CA (US)
Davide Scaini of Barcelona (ES)
AUTOMATIC GENERATION AND SELECTION OF TARGET PROFILES FOR DYNAMIC EQUALIZATION OF AUDIO CONTENT - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240022224 titled 'AUTOMATIC GENERATION AND SELECTION OF TARGET PROFILES FOR DYNAMIC EQUALIZATION OF AUDIO CONTENT
Simplified Explanation
The patent application describes a method for analyzing and categorizing audio content items based on their frequency bands and semantic labels. Here is a simplified explanation of the abstract:
- The method starts by filtering the reference audio content items into different frequency bands.
- For each frequency band, a first feature vector is extracted from a portion of each reference audio content item, capturing audio characteristics.
- Semantic labels are obtained from a portion of each reference audio content item.
- A second feature vector is created, consisting of the first feature vectors per frequency band and the semantic labels.
- Cluster feature vectors representing centroids of clusters are generated based on the second feature vector.
- The reference audio content items are separated according to the cluster feature vectors.
- An average target profile is computed for each cluster based on the reference audio content items in the cluster.
Potential applications of this technology:
- Audio content categorization and organization
- Music recommendation systems
- Speech recognition and transcription
- Audio content search and retrieval
Problems solved by this technology:
- Efficiently categorizing and organizing large volumes of audio content
- Improving the accuracy of audio content analysis and classification
- Enhancing the performance of audio-based recommendation systems
Benefits of this technology:
- Improved user experience in finding and accessing relevant audio content
- More accurate and personalized audio recommendations
- Time and cost savings in audio content management and analysis
Original Abstract Submitted
in an embodiment, a method comprises: filtering reference audio content items to separate the reference audio content items into different frequency bands; for each frequency band, extracting a first feature vector from at least a portion of each of the reference audio content items, wherein the first feature vector includes at least one audio characteristic of the reference audio content items; obtaining at least one semantic label from at least a portion of each of the reference audio content items; obtaining a second feature vector consisting of the first feature vectors per frequency band and the at least one semantic label; generating, based on the second feature vector, cluster feature vectors representing centroids of clusters; separating the reference audio content items according to the cluster feature vectors; and computing an average target profile for each cluster based on the reference audio content items in the cluster.
