English
Related papers

Related papers: DuoTok: Source-Aware Dual-Track Tokenization for M…

200 papers

Traffic forecasting is crucial for transportation systems optimisation. Current models minimise the mean forecasting errors, often favouring periodic events prevalent in the training data, while overlooking critical aperiodic ones like…

Machine Learning · Computer Science 2025-06-10 Xinyu Su , Feng Liu , Yanchuan Chang , Egemen Tanin , Majid Sarvi , Jianzhong Qi

This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…

Computation and Language · Computer Science 2025-12-30 Jeongsoo Choi , Jaehun Kim , Joon Son Chung

Back-translation (BT) of target monolingual corpora is a widely used data augmentation strategy for neural machine translation (NMT), especially for low-resource language pairs. To improve effectiveness of the available BT data, we…

Computation and Language · Computer Science 2021-09-10 Sahana Ramnath , Melvin Johnson , Abhirut Gupta , Aravindan Raghuveer

We propose an end-to-end music mixing style transfer system that converts the mixing style of an input multitrack to that of a reference song. This is achieved with an encoder pre-trained with a contrastive objective to extract only audio…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-12 Junghyun Koo , Marco A. Martínez-Ramírez , Wei-Hsiang Liao , Stefan Uhlich , Kyogu Lee , Yuki Mitsufuji

We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy. Motivated by recent work that predicts the probabilities of subsequent tokens using multiple heads, we…

Machine Learning · Computer Science 2025-02-11 Artem Basharin , Andrei Chertkov , Ivan Oseledets

Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chenhao Zheng , Jieyu Zhang , Jianing Zhang , Weikai Huang , Ashutosh Kumar , Quan Kong , Oncel Tuzel , Chun-Liang Li , Ranjay Krishna

Mixing style transfer automates the generation of a multitrack mix for a given set of tracks by inferring production attributes from a reference song. However, existing systems for mixing style transfer are limited in that they often…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-15 Soumya Sai Vanka , Christian Steinmetz , Jean-Baptiste Rolland , Joshua Reiss , George Fazekas

Automatic parallelization remains a challenging problem in software engineering, particularly in identifying code regions where loops can be safely executed in parallel on modern multi-core architectures. Traditional static analysis…

Software Engineering · Computer Science 2026-04-01 Izavan dos S. Correia , Henrique C. T. Santos , Tiago A. E. Ferreira

Multi-object tracking (MOT) is a critical technology in computer vision, designed to detect multiple targets in video sequences and assign each target a unique ID per frame. Existed MOT methods excel at accurately tracking multiple objects…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Lifan Jiang , Zhihui Wang , Siqi Yin , Guangxiao Ma , Peng Zhang , Boxi Wu

Despite there being clear evidence for top-down (e.g., attentional) effects in biological spatial hearing, relatively few machine hearing systems exploit top-down model-based knowledge in sound localisation. This paper addresses this issue…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-08 Ning Ma , Jose A. Gonzalez , Guy J. Brown

In automatic target recognition (ATR) systems, sensors may fail to capture discriminative, fine-grained detail features due to environmental conditions, noise created by CMOS chips, occlusion, parallaxes, and sensor misalignment. Therefore,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Shoaib Meraj Sami , Md Mahedi Hasan , Nasser M. Nasrabadi , Raghuveer Rao

Previous work has considered token overlap, or even similarity of token distributions, as predictors for multilinguality and cross-lingual knowledge transfer in language models. However, these very literal metrics assign large distances to…

Computation and Language · Computer Science 2025-02-11 Katharina Hämmerl , Tomasz Limisiewicz , Jindřich Libovický , Alexander Fraser

Real-world datasets for deep learning frequently suffer from the co-occurring challenges of class imbalance and label noise, hindering model performance. While methods exist for each issue, effectively combining them is non-trivial, as…

Machine Learning · Computer Science 2025-10-10 Feng Hong , Yu Huang , Zihua Zhao , Zhihan Zhou , Jiangchao Yao , Dongsheng Li , Ya Zhang , Yanfeng Wang

Transformer is a successful deep neural network (DNN) architecture that has shown its versatility not only in natural language processing but also in music information retrieval (MIR). In this paper, we present a novel Transformer-based…

Sound · Computer Science 2022-05-31 Yun-Ning Hung , Ju-Chiang Wang , Xuchen Song , Wei-Tsung Lu , Minz Won

This paper presents the \textbf{S}emantic-a\textbf{W}ar\textbf{E} spatial-t\textbf{E}mporal \textbf{T}okenizer (SweetTok), a novel video tokenizer to overcome the limitations in current video tokenization methods for compacted yet effective…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Zhentao Tan , Ben Xue , Jian Jia , Junhao Wang , Wencai Ye , Shaoyun Shi , Mingjie Sun , Wenjin Wu , Quan Chen , Peng Jiang

Speech-to-speech models handle turn-taking naturally but offer limited support for tool-calling or complex reasoning, while production ASR-LLM-TTS voice pipelines offer these capabilities but rely on silence timeouts, which lead to…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-10 Shangeth Rajaa

We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Yang Jiao , Haibo Qiu , Zequn Jie , Shaoxiang Chen , Jingjing Chen , Lin Ma , Yu-Gang Jiang

Neural Speech Codecs face a fundamental trade-off at low bitrates: preserving acoustic fidelity often compromises semantic richness. To address this, we introduce SACodec, a novel codec built upon an asymmetric dual-quantizer that employs…

Sound · Computer Science 2025-12-25 Zhongren Dong , Bin Wang , Jing Han , Haotian Guo , Xiaojun Mo , Yimin Cao , Zixing Zhang

Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods often degrade video…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Wonsuk Jang , Thierry Tambe

Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation. Achieving high quality and diversity in this process demands extensive, high-quality data, which are often…

Sound · Computer Science 2025-06-18 Chang Li , Ruoyu Wang , Lijuan Liu , Jun Du , Yixuan Sun , Zilu Guo , Zhenrong Zhang , Yuan Jiang , Jianqing Gao , Feng Ma