Picture for Hongyu Xiang

Hongyu Xiang

CPPF: A contextual and post-processing-free model for automatic speech recognition

Add code
Sep 21, 2023
Viaarxiv icon

Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First Regularization

Add code
Nov 07, 2022
Viaarxiv icon

CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR

Add code
Mar 31, 2022
Figure 1 for CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR
Figure 2 for CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR
Figure 3 for CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR
Figure 4 for CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR
Viaarxiv icon

CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency

Add code
May 27, 2020
Figure 1 for CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency
Figure 2 for CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency
Figure 3 for CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency
Figure 4 for CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency
Viaarxiv icon

CAT: CRF-based ASR Toolkit

Add code
Nov 20, 2019
Figure 1 for CAT: CRF-based ASR Toolkit
Figure 2 for CAT: CRF-based ASR Toolkit
Figure 3 for CAT: CRF-based ASR Toolkit
Figure 4 for CAT: CRF-based ASR Toolkit
Viaarxiv icon