Convolutional Recurrent Neural Networks for Speech Activity Detection in Naturalistic Audio from Apollo Missions.
Pablo GimenoDayana RibasAlfonso Ortega GiménezAntonio MiguelEduardo LleidaPublished in: IberSPEECH (2021)
Keyphrases
- recurrent neural networks
- smart room
- speaker diarization
- neural network
- feed forward
- artificial neural networks
- broadcast news
- reservoir computing
- multimedia
- visual data
- echo state networks
- recurrent networks
- cascade correlation
- visual information
- nonlinear dynamic systems
- audio visual
- speaker identification
- music information retrieval
- unsupervised learning
- high dimensional
- machine learning