Audio Captioning using Gated Recurrent Units.
Aysegül Özkaya ErenMustafa SertPublished in: CoRR (2020)
Keyphrases
- multimedia
- audio visual
- recurrent neural networks
- visual information
- multi unit combinatorial auctions
- audio video
- music information retrieval
- feed forward
- signal processing
- database
- video streams
- computer vision
- processing units
- cross modal
- audio signal
- databases
- cepstral features
- music score
- audio files
- real time
- spiking neural networks
- video recordings
- broadcast news
- audio features
- digital video
- neural network
- machine learning
- case study
- back propagation