User-guided adaptive playlisting using joint audio-text embeddings
- Applicant
- Auteurs
- N/A
- Titre
- User-guided adaptive playlisting using joint audio-text embeddings
- Patent Number
- WO2024043931
- Publication Date
- 2024
- uri
- https://patents.google.com/patent/WO2024043931
- Description
- A method includes providing, by an audio playback interface, an initial playlist comprising audio tracks. The method includes receiving a user preference associated with an initial audio track during a listening session, wherein the user preference is indicative of a listening mood of a user and comprises one or more of a user behavior or a natural language input. The method includes generating a representation of the user preference in a joint audio- text embedding space by applying a two-tower model comprising an audio embedding network and a text embedding network. A proximity of two embeddings is indicative of semantic similarity. The method includes training a machine learning model to generate an updated playlist responsive to the listening mood of the user during the listening session. The method includes applying the machine learning model to generate the updated playlist. The method includes substituting the initial playlist with the updated playlist.
- keywords
- Mood
- Domaine de recherche
- Human-Computer Interaction & User Experience
- Natural Language Processing
- Sentiment Analysis
- Software Development
- Données collectées (type source)
- Text
- Audio
- Media Content
- Concepts clés
- Listening mood
- Méthode
- The mood of the user may be inferred by analyzing listen/skip behavior and/or based on user-provided natural-language inputs describing their current interests
- Dispositif
- Device
- Objectifs du brevet
- Personalize/Improve with emotion information
- Pages du site
- Contenu
Fait partie de User-guided adaptive playlisting using joint audio-text embeddings