About this document
Active Speaker Detection Using Audio Visual and Depth Modalities A Survey by Rodrigo Galhardo is a document available to read on EtoBox.
The document presents a comprehensive survey on Active Speaker Detection (ASD) using audio, visual, and depth modalities, highlighting its significance in applications like voice recognition and speaker diarization. It categorizes ASD methods into single and multi-modality approaches, detailing various techniques and datasets utilized in the field. The paper also discusses challenges and future research directions to enhance the effectiveness of ASD systems.
- Author
- Rodrigo Galhardo
- Language
- EN