End-to-end Multi-modal Low-resourced Speech Keywords Recognition Using Sequential Conv2D Nets.
Pooja GambhirAmita DevPoonam BansalDeepak Kumar SharmaPublished in: ACM Trans. Asian Low Resour. Lang. Inf. Process. (2024)
Keyphrases
- multi modal
- end to end
- audio visual
- keywords
- wireless ad hoc networks
- multi modality
- speech recognition
- high dimensional
- congestion control
- admission control
- uni modal
- internet protocol
- semantic information
- video search
- speech signal
- scalable video
- application layer
- cross modal
- multimedia
- visual features
- feature extraction