English
Related papers

Related papers: CSF: Contrastive Semantic Features for Direct Mult…

200 papers

Sign language is a visual language used by the deaf and dumb community to communicate. However, for most recognition methods based on monocular cameras, the recognition accuracy is low and the robustness is poor. Even if the effect is good…

Computer Vision and Pattern Recognition · Computer Science 2024-07-03 Zhiyu Long , Xingyou Liu , Jiaqi Qiao , Zhi Li

Precision oncology is currently limited by the small-N, large-P paradox, where high-dimensional genomic data is abundant but pharmacological response samples are sparse. While deep learning achieves predictive accuracy, it frequently fails…

Quantitative Methods · Quantitative Biology 2026-05-11 Christopher Baker , Karen Rafferty , Hui Wang

Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-12 Xuan Shi , Chang Zeng , Tiantian Feng , Shih-Heng Wang , Jianbo Ma , Shrikanth Narayanan

In this paper, we present a new open source toolkit for automatic speech recognition (ASR), named CAT (CRF-based ASR Toolkit). A key feature of CAT is discriminative training in the framework of conditional random field (CRF), particularly…

Machine Learning · Computer Science 2019-11-21 Keyu An , Hongyu Xiang , Zhijian Ou

Classifier-Free Guidance (CFG) has been widely used in text-to-image diffusion models, where the CFG scale is introduced to control the strength of text guidance on the whole image space. However, we argue that a global CFG scale results in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Dazhong Shen , Guanglu Song , Zeyue Xue , Fu-Yun Wang , Yu Liu

In this paper, we present a novel approach to natural language understanding that utilizes context-free grammars (CFGs) in conjunction with sequence-to-sequence (seq2seq) deep learning. Specifically, we take a CFG authored to generate…

Computation and Language · Computer Science 2016-07-26 Adam James Summerville , James Ryan , Michael Mateas , Noah Wardrip-Fruin

Connectionist Temporal Classification (CTC) based end-to-end speech recognition system usually need to incorporate an external language model by using WFST-based decoding in order to achieve promising results. This is more essential to…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-24 Shiliang Zhang , Ming Lei , Zhijie Yan

Cued Speech (CS) is a communication system developed for deaf people, which exploits hand cues to complement speechreading at the phonetic level. Currently, it is estimated that CS has been adapted to over 60 languages; however, no official…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-06 Liu Li , Feng Gang

Contextual information plays a core role for video semantic segmentation (VSS). This paper summarizes contexts for VSS in two-fold: local temporal contexts (LTC) which define the contexts from neighboring frames, and global temporal…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Guolei Sun , Yun Liu , Henghui Ding , Min Wu , Luc Van Gool

Classifier-Free Guidance (CFG) significantly enhances controllability in generative models by interpolating conditional and unconditional predictions. However, standard CFG often employs a static unconditional input, which can be suboptimal…

Computation and Language · Computer Science 2025-05-27 Pengxiang Li , Shilin Yan , Joey Tsai , Renrui Zhang , Ruichuan An , Ziyu Guo , Xiaowei Gao

Sign Languages are rich multi-channel languages, requiring articulation of both manual (hands) and non-manual (face and body) features in a precise, intricate manner. Sign Language Production (SLP), the automatic translation from spoken to…

Computer Vision and Pattern Recognition · Computer Science 2020-08-31 Ben Saunders , Necati Cihan Camgoz , Richard Bowden

This paper presents a novel speaking-style captioning method that generates diverse descriptions while accurately predicting speaking-style information. Conventional learning criteria directly use original captions that contain not only…

Computation and Language · Computer Science 2024-06-28 Atsushi Ando , Takafumi Moriya , Shota Horiguchi , Ryo Masumura

Previous CCG supertaggers usually predict categories using multi-class classification. Despite their simplicity, internal structures of categories are usually ignored. The rich semantics inside these structures may help us to better handle…

Computation and Language · Computer Science 2021-03-16 Yufang Liu , Tao Ji , Yuanbin Wu , Man Lan

The current bottleneck in continuous sign language recognition (CSLR) research lies in the fact that most publicly available datasets are limited to laboratory environments or television program recordings, resulting in a single background…

Computer Vision and Pattern Recognition · Computer Science 2025-09-11 Qidan Zhu , Jing Li , Fei Yuan , Jiaojiao Fan , Quan Gan

We outline a bidirectional translation system that converts sentences from American Sign Language (ASL) to English, and vice versa. To perform machine translation between ASL and English, we utilize a generative approach. Specifically, we…

Computation and Language · Computer Science 2017-01-12 Hardie Cate , Zeshan Hussain

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Audio and Speech Processing · Electrical Eng. & Systems 2018-08-22 Shruti Palaskar , Florian Metze

Continuous Sign Language Recognition (CSLR) focuses on the interpretation of a sequence of sign language gestures performed continually without pauses. In this study, we conduct an empirical evaluation of recent deep learning CSLR…

Computation and Language · Computer Science 2024-10-23 Sarah Alyami , Hamzah Luqman

Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Shayan Jalilian , Abdul Bais

More than half of the 7,000 languages in the world are in imminent danger of going extinct. Traditional methods of documenting language proceed by collecting audio data followed by manual annotation by trained linguists at different levels…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-06 Sameer Khurana , Antoine Laurent , James Glass

One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning…

Computation and Language · Computer Science 2016-08-08 Mohammad Taher Pilehvar , Nigel Collier