English
Related papers

Related papers: SpecASR: Accelerating LLM-based Automatic Speech R…

200 papers

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…

Computation and Language · Computer Science 2026-04-15 Zhuofan Wen , Yang Feng

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In…

Large language model (LLM)-based automatic speech recognition (ASR) has recently achieved strong performance across diverse tasks, yet contextual biasing for named entities and hotwords under large vocabularies remains challenging. In this…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-29 YuXiang Kong , JunFeng Hou , Jian Tang , Bingqing Zhu , Jicheng Zhang , Shaofei Xue

Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-06 Jeena Prakash , Blessingh Kumar , Kadri Hacioglu , Bidisha Sharma , Sindhuja Gopalan , Malolan Chetlur , Shankar Venkatesan , Andreas Stolcke

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the…

Machine Learning · Computer Science 2026-04-14 Jingwei Song , Xinyu Wang , Hanbin Wang , Xiaoxuan Lei , Bill Shi , Shixin Han , Eric Yang , Xiao-Wen Chang , Lynn Ai

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Computation and Language · Computer Science 2025-06-12 Nadav Timor , Jonathan Mamou , Daniel Korat , Moshe Berchansky , Gaurav Jain , Oren Pereg , Moshe Wasserblat , David Harel

Vision-Language Models (VLMs) enable powerful multimodal reasoning but suffer from slow autoregressive inference, limiting their deployment in real-time applications. We introduce Spec-LLaVA, a system that applies speculative decoding to…

Computation and Language · Computer Science 2025-09-16 Mingxiao Huo , Jiayi Zhang , Hewei Wang , Jinfeng Xu , Zheyu Chen , Huilin Tai , Yijun Chen

Large language models have proven themselves highly flexible, able to solve a wide range of generative tasks, such as abstractive summarization and open-ended question answering. In this paper we extend the capabilities of LLMs by directly…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-25 Yassir Fathullah , Chunyang Wu , Egor Lakomkin , Junteng Jia , Yuan Shangguan , Ke Li , Jinxi Guo , Wenhan Xiong , Jay Mahadeokar , Ozlem Kalinli , Christian Fuegen , Mike Seltzer

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Computation and Language · Computer Science 2025-05-14 Danying Ge , Jianhua Gao , Qizhi Jiang , Yifei Feng , Weixing Ji

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-16 Ziyi Zhang , Ziheng Jiang , Chengquan Jiang , Menghan Yu , Size Zheng , Haibin Lin , Henry Hoffmann , Xin Liu

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

Computation and Language · Computer Science 2025-02-11 Jun Zhang , Jue Wang , Huan Li , Lidan Shou , Ke Chen , Gang Chen , Sharad Mehrotra

Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in…

Machine Learning · Computer Science 2025-10-31 Qiaoling Chen , Zijun Liu , Peng Sun , Shenggui Li , Guoteng Wang , Ziming Liu , Yonggang Wen , Siyuan Feng , Tianwei Zhang

Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly acute for test-time scaling methods such as parallel…

Machine Learning · Computer Science 2026-03-24 Yuanlin Chu , Bo Wang , Xiang Liu , Hong Chen , Aiwei Liu , Xuming Hu

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Computation and Language · Computer Science 2025-06-24 Guanzheng Chen , Qilong Feng , Jinjie Ni , Xin Li , Michael Qizhe Shieh

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

Computation and Language · Computer Science 2019-10-24 Oleksii Hrinchuk , Mariya Popova , Boris Ginsburg

Large language models (LLMs) have revolutionized natural language processing and broadened their applicability across diverse commercial applications. However, the deployment of these models is constrained by high inference time in…

Computation and Language · Computer Science 2024-11-12 Euiin Yi , Taehyeon Kim , Hongseok Jeung , Du-Seong Chang , Se-Young Yun

We propose self-speculative decoding for speech-aware LLMs by using the CTC encoder as a draft model to accelerate auto-regressive (AR) inference and improve ASR accuracy. Our three-step procedure works as follows: (1) if the frame…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-13 George Saon , Samuel Thomas , Takashi Fukuda , Tohru Nagano , Avihu Dekel , Luis Lastras

Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and speech domains, an LLM can be equipped with (automatic)…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Umberto Cappellazzo , Minsu Kim , Honglie Chen , Pingchuan Ma , Stavros Petridis , Daniele Falavigna , Alessio Brutti , Maja Pantic

Speculative Decoding (SD) is a popular lossless technique for accelerating the inference of Large Language Models (LLMs). We show that the decoding speed of SD frameworks with static draft structures can be significantly improved by…

Artificial Intelligence · Computer Science 2024-12-30 Situo Zhang , Hankun Wang , Da Ma , Zichen Zhu , Lu Chen , Kunyao Lan , Kai Yu

As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…

Computation and Language · Computer Science 2025-10-06 Guanghao Li , Zhihui Fu , Min Fang , Qibin Zhao , Ming Tang , Chun Yuan , Jun Wang