English
Related papers

Related papers: Make Some Noise: Unlocking Language Model Parallel…

200 papers

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…

Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual…

Computation and Language · Computer Science 2024-03-06 Yifu Sun , Haoming Jiang

The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference…

Deep learning (DL) has shown promise for faster, high quality accelerated MRI reconstruction. However, supervised DL methods depend on extensive amounts of fully-sampled (labeled) data and are sensitive to out-of-distribution (OOD) shifts,…

Noise injection is a fundamental tool for data augmentation, and yet there is no widely accepted procedure to incorporate it with learning frameworks. This study analyzes the effects of adding or applying different noise models of varying…

Computer Vision and Pattern Recognition · Computer Science 2023-07-14 M. Eren Akbiyik

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

Computation and Language · Computer Science 2021-06-11 Christos Baziotis , Ivan Titov , Alexandra Birch , Barry Haddow

Neural language models do not scale well when the vocabulary is large. Noise-contrastive estimation (NCE) is a sampling-based method that allows for fast learning with large vocabularies. Although NCE has shown promising performance in…

Computation and Language · Computer Science 2017-09-25 Farhana Ferdousi Liza , Marek Grzes

This paper presents a simple method that allows to easily enhance textual pre-trained large language models with speech information, when fine-tuned for a specific classification task. A classical issue with the fusion of many embeddings…

Computation and Language · Computer Science 2026-04-07 Nicolas Calbucura , Jose Guillen , Valentin Barriere

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…

Computation and Language · Computer Science 2024-04-19 Pengfei Wu , Jiahao Liu , Zhuocheng Gong , Qifan Wang , Jinpeng Li , Jingang Wang , Xunliang Cai , Dongyan Zhao

Learning from corrupted labels is very common in real-world machine-learning applications. Memorizing such noisy labels could affect the learning of the model, leading to sub-optimal performances. In this work, we propose a novel framework…

Machine Learning · Computer Science 2023-12-20 Yu Wang , Xin Xin , Zaiqiao Meng , Joemon Jose , Fuli Feng

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

Computation and Language · Computer Science 2025-06-24 Kang Chen , Mengdi Zhang , Yixin Cao

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…

Computation and Language · Computer Science 2024-06-05 Heming Xia , Zhe Yang , Qingxiu Dong , Peiyi Wang , Yongqi Li , Tao Ge , Tianyu Liu , Wenjie Li , Zhifang Sui

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Subhasis Dasgupta , Hetvi Waghela

Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. A possible solution is to transfer hints during inference from…

Machine Learning · Computer Science 2024-07-26 Vidya Srinivas , Malek Itani , Tuochao Chen , Sefik Emre Eskimez , Takuya Yoshioka , Shyamnath Gollakota

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

Machine Learning · Computer Science 2026-03-02 Feng Chen , Yefei He , Lequan Lin , Chenhui Gou , Jing Liu , Bohan Zhuang , Qi Wu

The massive amounts of web-mined parallel data contain large amounts of noise. Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems. In this paper, we first introduce a…

Computation and Language · Computer Science 2025-02-10 Yan Meng , Di Wu , Christof Monz

The immense model sizes of large language models (LLMs) challenge deployment on memory-limited consumer GPUs. Although model compression and parameter offloading are common strategies to address memory limitations, compression can degrade…

Computation and Language · Computer Science 2025-10-10 Pei-Shuo Wang , Jian-Jia Chen , Chun-Che Yang , Chi-Chih Chang , Ning-Chi Huang , Mohamed S. Abdelfattah , Kai-Chiang Wu

The lack of clean speech is a practical challenge to the development of speech enhancement systems, which means that there is an inevitable mismatch between their training criterion and evaluation metric. In response to this unfavorable…

Sound · Computer Science 2023-05-23 Li-Wei Chen , Yao-Fei Cheng , Hung-Shin Lee , Yu Tsao , Hsin-Min Wang

Recent single-channel speech enhancement methods based on deep neural networks (DNNs) have achieved remarkable results, but there are still generalization problems in real scenes. Like other data-driven methods, DNN-based speech enhancement…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-12 Lu Zhang , Mingjiang Wang , Andong Li , Zehua Zhang , Xuyi Zhuang

Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…

Computation and Language · Computer Science 2026-05-27 Zhiyang Chen , Daliang Xu , Yinyuan Zhang , Chenghua Wang , Mengwei Xu , Yun Ma