Picture for Qijie Shao

Qijie Shao

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models

Add code
Sep 30, 2024
Figure 1 for HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
Figure 2 for HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
Figure 3 for HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
Figure 4 for HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models
Viaarxiv icon

Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text

Add code
Sep 17, 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

Decoupling and Interacting Multi-Task Learning Network for Joint Speech and Accent Recognition

Add code
Nov 17, 2023
Viaarxiv icon

SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition

Add code
Sep 29, 2023
Viaarxiv icon

TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition

Add code
May 23, 2023
Viaarxiv icon

Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition

Add code
Apr 07, 2022
Figure 1 for Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition
Figure 2 for Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition
Figure 3 for Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition
Figure 4 for Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition
Viaarxiv icon

WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition

Add code
Oct 18, 2021
Figure 1 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 2 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 3 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Figure 4 for WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Viaarxiv icon

Auto-KWS 2021 Challenge: Task, Datasets, and Baselines

Add code
Mar 31, 2021
Figure 1 for Auto-KWS 2021 Challenge: Task, Datasets, and Baselines
Figure 2 for Auto-KWS 2021 Challenge: Task, Datasets, and Baselines
Figure 3 for Auto-KWS 2021 Challenge: Task, Datasets, and Baselines
Figure 4 for Auto-KWS 2021 Challenge: Task, Datasets, and Baselines
Viaarxiv icon

The NPU System for the 2020 Personalized Voice Trigger Challenge

Add code
Feb 26, 2021
Figure 1 for The NPU System for the 2020 Personalized Voice Trigger Challenge
Figure 2 for The NPU System for the 2020 Personalized Voice Trigger Challenge
Figure 3 for The NPU System for the 2020 Personalized Voice Trigger Challenge
Figure 4 for The NPU System for the 2020 Personalized Voice Trigger Challenge
Viaarxiv icon