MaLa-ASR: Multimedia-Assisted LLM-Based ASR

MaLa-ASR: Multimedia-Assisted LLM-Based ASR

9 June 2024

Ziyang Ma

Shiliang Zhang

Xie Chen

Papers citing "MaLa-ASR: Multimedia-Assisted LLM-Based ASR"

6 / 6 papers shown

Title
Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM Fengrun Zhang Wang Geng Hukai Huang Cheng Yi He Qu He Qu AuLLM MoE 28 1 0 24 Sep 2024
Language Model Can Listen While Speaking Ziyang Ma Yakun Song Chenpeng Du Jian Cong Zhuo Chen Yuping Wang Y. Wang Xie Chen AuLLM 29 23 0 05 Aug 2024
An Embarrassingly Simple Approach for LLM with Strong ASR Capacity Ziyang Ma Guanrou Yang Yifan Yang Zhifu Gao Jiaming Wang ... Fan Yu Qian Chen Siqi Zheng Shiliang Zhang Xie Chen AuLLM 47 37 0 13 Feb 2024
End-to-End Speech Recognition Contextualization with Large Language Models Egor Lakomkin Chunyang Wu Yassir Fathullah Ozlem Kalinli M. Seltzer Christian Fuegen 47 17 0 19 Sep 2023
End-to-end Audio-visual Speech Recognition with Conformers Pingchuan Ma Stavros Petridis M. Pantic 79 221 0 12 Feb 2021
VoxCeleb2: Deep Speaker Recognition Joon Son Chung Arsha Nagrani Andrew Zisserman 214 1,954 0 14 Jun 2018