Picture for Yeon-Jun Kim

Yeon-Jun Kim

1SPU: 1-step Speech Processing Unit

Add code
Nov 10, 2023
Viaarxiv icon

E2E Spoken Entity Extraction for Virtual Agents

Add code
Mar 01, 2023
Viaarxiv icon

Cross-stitched Multi-modal Encoders

Add code
Apr 20, 2022
Figure 1 for Cross-stitched Multi-modal Encoders
Figure 2 for Cross-stitched Multi-modal Encoders
Figure 3 for Cross-stitched Multi-modal Encoders
Figure 4 for Cross-stitched Multi-modal Encoders
Viaarxiv icon

Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture

Add code
Mar 29, 2022
Figure 1 for Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture
Figure 2 for Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture
Figure 3 for Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture
Figure 4 for Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture
Viaarxiv icon