Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features.
Gautam KrishnaSameer DharurOggi RudovicPranay DigheSaurabh AdyaAhmed Hussen AbdelazizAhmed H. TewfikPublished in: CoRR (2023)
Keyphrases
- multi modal
- false positives
- feature vectors
- audio visual
- feature extraction
- multimedia
- co occurrence
- feature set
- support vector machine classifier
- multi stream
- multimodal interaction
- detection method
- object detection
- speech recognition
- detection algorithm
- keypoints
- feature detection
- human computer interaction
- automatic speech recognition
- human detection
- multiple modalities
- image features
- low level