English
Related papers

Related papers: Let's Fuse Step by Step: A Generative Fusion Decod…

200 papers

Recent studies have successfully shown that large language models (LLMs) can be successfully used for generative error correction (GER) on top of the automatic speech recognition (ASR) output. Specifically, an LLM is utilized to carry out a…

Computation and Language · Computer Science 2024-02-09 Chen Chen , Ruizhe Li , Yuchen Hu , Sabato Marco Siniscalchi , Pin-Yu Chen , Ensiong Chng , Chao-Han Huck Yang

The joint training framework for speech enhancement and recognition methods have obtained quite good performances for robust end-to-end automatic speech recognition (ASR). However, these methods only utilize the enhanced feature as the…

Sound · Computer Science 2020-11-10 Cunhang Fan , Jiangyan Yi , Jianhua Tao , Zhengkun Tian , Bin Liu , Zhengqi Wen

We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate…

This paper presents an efficient decoding approach for end-to-end automatic speech recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the most common approach to incorporate language models into E2E-ASR…

Computation and Language · Computer Science 2025-01-17 Takaaki Hori , Martin Kocour , Adnan Haider , Erik McDermott , Xiaodan Zhuang

While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific…

Computation and Language · Computer Science 2025-07-17 Shilin Zhou , Zhenghua Li

The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard decoding methods often fail to robustly satisfy these…

Training automatic speech recognition (ASR) models increasingly relies on decentralized federated learning to ensure data privacy and accessibility, producing multiple local models that require effective merging. In hybrid ASR systems,…

Computation and Language · Computer Science 2026-03-06 Mengze Hong , Yi Gu , Di Jiang , Hanlin Gu , Chen Jason Zhang , Lu Wang , Zhiyang Su

Retrieval-augmented generation (RAG) incorporates external knowledge into large language models (LLMs), improving their adaptability to downstream tasks and enabling information updates. Surprisingly, recent empirical evidence demonstrates…

Computation and Language · Computer Science 2026-01-08 Yang Sun , Zhiyong Xie , Lixin Zou , Dan Luo , Min Tang , Xiangyu Zhao , Yunwei Zhao , Xixun Lin , Yanxiong Lu , Chenliang Li

We propose a new shallow fusion (SF) method to exploit an external backward language model (BLM) for end-to-end automatic speech recognition (ASR). The BLM has complementary characteristics with a forward language model (FLM), and the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-22 Atsunori Ogawa , Takafumi Moriya , Naoyuki Kamo , Naohiro Tawara , Marc Delcroix

Multimodal learning faces a fundamental tension between deep, fine-grained fusion and computational scalability. While cross-attention models achieve strong performance through exhaustive pairwise fusion, their quadratic complexity is…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Yusuf Shihata

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

Computation and Language · Computer Science 2025-10-06 Wenrui Bao , Zhiben Chen , Dan Xu , Yuzhang Shang

The goal of this work is to enhance balanced multimodal understanding in audio-visual large language models (AV-LLMs) by addressing modality bias without additional training. In current AV-LLMs, audio and video features are typically…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Chaeyoung Jung , Youngjoon Jang , Jongmin Choi , Joon Son Chung

Large Language Models (LLMs) often excel in specific domains but fall short in others due to the limitations of their training. Thus, enabling LLMs to solve problems collaboratively by integrating their complementary knowledge promises to…

Computation and Language · Computer Science 2025-03-20 Ziyao Wang , Muneeza Azmat , Ang Li , Raya Horesh , Mikhail Yurochkin

Recent research on integrating Large Language Models (LLMs) with Graph Neural Networks (GNNs) typically follows two approaches: LLM-centered models, which convert graph data into tokens for LLM processing, and GNN-centered models, which use…

Machine Learning · Computer Science 2024-12-11 Haotong Yang , Xiyuan Wang , Qian Tao , Shuxian Hu , Zhouchen Lin , Muhan Zhang

Large Vision-Language Models (LVLMs) have shown strong performance across multimodal tasks. However, they often produce hallucinations -- text that is inconsistent with visual input, due to the limited ability to verify information in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Haonan Ge , Yiwei Wang , Ming-Hsuan Yang , Yujun Cai

Large Language Models (LLMs) are often asked to generate structured outputs that obey precise syntactic rules, such as code snippets or formatted data. Grammar-constrained decoding (GCD) can guarantee that LLM outputs matches such rules by…

Computation and Language · Computer Science 2025-07-17 Kanghee Park , Timothy Zhou , Loris D'Antoni

Integrating Pre-trained Language Models (PLMs) with Graph Neural Networks (GNNs) remains a central challenge in text-rich heterophilic graph learning. We propose a novel integration framework that enables effective fusion between powerful…

Computation and Language · Computer Science 2025-10-09 Aarush Sinha

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

Sound · Computer Science 2026-01-27 Wenjie Tian , Bingshen Mu , Guobin Ma , Xuelong Geng , Zhixian Zhao , Lei Xie

Among the representation learning, the low-rank representation (LRR) is one of the hot research topics in many fields, especially in image processing and pattern recognition. Although LRR can capture the global structure, the ability of…

Computer Vision and Pattern Recognition · Computer Science 2018-12-19 Hui Li , Xiao-Jun Wu

This research introduces a transformative framework for integrating Vision-Enhanced Large Language Models (LLMs) with advanced transformer-based architectures to tackle challenges in high-resolution image synthesis and multimodal data…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Karthikeya KV
‹ Prev 1 2 3 10 Next ›