UNSUPERVISED LEARNING OF SEMANTIC AUDIO REPRESENTATIONS

UNSUPERVISED LEARNING OF SEMANTIC AUDIO REPRESENTATIONS

Methods are provided for generating training triplets that can be used to train multidimensional embeddings to represent the semantic content of non-speech sounds present in a corpus of audio recordings. These training triplets can be used with a triplet loss function to train the multidimensional e...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ELLIS, Daniel, JANSEN, Aren, MOORE, Richard, Channing, PLAKAL, Manoj, PANDYA, Ratheet, LIU, Jiayang, RIFKIN, Ryan, HERSHEY, Shawn
Format: Patent
Sprache:eng ; fre ; ger
Schlagworte:
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Methods are provided for generating training triplets that can be used to train multidimensional embeddings to represent the semantic content of non-speech sounds present in a corpus of audio recordings. These training triplets can be used with a triplet loss function to train the multidimensional embeddings such that the embeddings can be used to cluster the contents of a corpus of audio recordings, to facilitate a query-by-example lookup from the corpus, to allow a small number of manually-labeled audio recordings to be generalized, or to facilitate some other audio classification task. The triplet sampling methods may be used individually or collectively, and each represent a respective heuristic about the semantic structure of audio recordings.