Picture for Naijun Zheng

Naijun Zheng

XCB: an effective contextual biasing approach to bias cross-lingual phrases in speech recognition

Add code
Aug 20, 2024
Viaarxiv icon

An efficient text augmentation approach for contextualized Mandarin speech recognition

Add code
Jun 14, 2024
Viaarxiv icon

MMGER: Multi-modal and Multi-granularity Generative Error Correction with LLM for Joint Accent and Speech Recognition

Add code
May 06, 2024
Viaarxiv icon

BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition

Add code
Oct 08, 2023
Viaarxiv icon

Partially Fake Audio Detection by Self-attention-based Fake Span Discovery

Add code
Feb 15, 2022
Figure 1 for Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Figure 2 for Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Figure 3 for Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Figure 4 for Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Viaarxiv icon

The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge

Add code
Feb 04, 2022
Figure 1 for The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
Figure 2 for The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
Figure 3 for The CUHK-TENCENT speaker diarization system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
Viaarxiv icon