activity
20182025
most citedRecent Developments on ESPnet Toolkit Boosted by Conformer

40 citations · 132 across the 39 of their papers we have counts for

collaborators
Showing cs.SDShow all

23 papers · 1 filter

cs.SD2025

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition

Bingshen Mu, Kun Wei, Pengcheng Guo +1

Despite improvements in automatic speech recognition, performance drops with accented speech. Generative error correction (GER) leverages the linguistic knowledge of large language…

cs.SD2025★ 1 cited

OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia

Xuelong Geng, Kun Wei, Qijie Shao +18

Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable compreh…

cs.SD2025

DiffAttack: Diffusion-based Timbre-reserved Adversarial Attack in Speaker Identification

Qing Wang, Jixun Yao, Zhaokai Sun +3

Being a form of biometric identification, the security of the speaker identification (SID) system is of utmost importance. To better understand the robustness of SID systems, we ai…

cs.SD2024

Optimizing Dysarthria Wake-Up Word Spotting: An End-to-End Approach for SLT 2024 LRDWWS Challenge

Shuiyun Liu, Yuxiang Kong, Pengcheng Guo +4

Speech has emerged as a widely embraced user interface across diverse applications. However, for individuals with dysarthria, the inherent variability in their speech poses signifi…

cs.SD2024

Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets

Xuelong Geng, Tianyi Xu, Kun Wei +9

Large Language Models (LLMs) have demonstrated unparalleled effectiveness in various NLP tasks, and integrating LLMs with automatic speech recognition (ASR) is becoming a mainstrea…

cs.SD2024★ 1 cited

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge

He Wang, Pengcheng Guo, Yue Li +13

To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2…