English
Related papers

Related papers: Decoding visemes: improving machine lipreading

200 papers

Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabilities remain under-explored. In this work, we conduct a comprehensive evaluation of both…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Illia Volkov , Nikita Kisel , Klara Janouskova , Jiri Matas

Speaker extraction algorithm relies on the speech sample from the target speaker as the reference point to focus its attention. Such a reference speech is typically pre-recorded. On the other hand, the temporal synchronization between…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-11 Zexu Pan , Ruijie Tao , Chenglin Xu , Haizhou Li

This paper presents an efficient visual speech encoder for lip reading. While most recent lip reading studies have been based on the ResNet architecture and have achieved significant success, they are not sufficiently suitable for…

Computer Vision and Pattern Recognition · Computer Science 2025-05-09 Young-Hu Park , Rae-Hong Park , Hyung-Min Park

Recent advancements in text-to-speech and speech conversion technologies have enabled the creation of highly convincing synthetic speech. While these innovations offer numerous practical benefits, they also cause significant security…

Sound · Computer Science 2024-12-18 Kuiyuan Zhang , Zhongyun Hua , Rushi Lan , Yushu Zhang , Yifang Guo

In social network service platforms, crime suspects are likely to use cybercrime coded words for communication by adding criminal meanings to existing words or replacing them with similar words. For instance, the word 'ice' is often used to…

Computation and Language · Computer Science 2024-03-19 Yongyeon Kim , Byung-Won On , Ingyu Lee

The aim of this work is to investigate the impact of crossmodal self-supervised pre-training for speech reconstruction (video-to-audio) by leveraging the natural co-occurrence of audio and visual streams in videos. We propose LipSound2…

Sound · Computer Science 2022-09-13 Leyuan Qu , Cornelius Weber , Stefan Wermter

In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, but these methods also pose potential and severe security threats to humanity. DeepFake can be bifurcated into entertainment…

Computer Vision and Pattern Recognition · Computer Science 2024-10-29 Weifeng Liu , Tianyi She , Jiawei Liu , Boheng Li , Dongyu Yao , Ziyou Liang , Run Wang

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and…

Computation and Language · Computer Science 2021-04-21 Wei Zhou , Simon Berger , Ralf Schlüter , Hermann Ney

Lip reading is vital for robots in social settings, improving their ability to understand human communication. This skill allows them to communicate more easily in crowded environments, especially in caregiving and customer service roles.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Ali Farshian Abbasi , Aghil Yousefi-Koma , Soheil Dehghani Firouzabadi , Parisa Rashidi , Alireza Naeini

Learning-based image compression methods have emerged as state-of-the-art, showcasing higher performance compared to conventional compression solutions. These data-driven approaches aim to learn the parameters of a neural network model…

Multimedia · Computer Science 2024-03-20 Shima Mohammadi , Yaojun Wu , João Ascenso

Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user's playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during…

Computation and Language · Computer Science 2019-07-23 Ke Hu , Antoine Bruguier , Tara N. Sainath , Rohit Prabhavalkar , Golan Pundak

While learning based compression techniques for images have outperformed traditional methods, they have not been widely adopted in machine learning pipelines. This is largely due to lack of standardization and lack of retention of salient…

Image and Video Processing · Electrical Eng. & Systems 2024-10-01 Kartik Gupta , Kimberley Faria , Vikas Mehta

Currently, the most dominant approach to establishing language-image alignment is to pre-train text and image encoders jointly through contrastive learning, such as CLIP and its variants. In this work, we question whether such a costly…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Jingfeng Yang , Ziyang Wu , Yue Zhao , Yi Ma

We present a novel language-driven ordering alignment method for ordinal classification. The labels in ordinal classification contain additional ordering relations, making them prone to overfitting when relying solely on training data.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Rui Wang , Peipei Li , Huaibo Huang , Chunshui Cao , Ran He , Zhaofeng He

Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…

Artificial Intelligence · Computer Science 2025-07-22 Nicolas Wischermann , Claudio Mayrink Verdun , Gabriel Poesia , Francesco Noseda

In this paper we deal with image classification tasks using the powerful CLIP vision-language model. Our goal is to advance the classification performance using the CLIP's image encoder, by proposing a novel Large Multimodal Model (LMM)…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Maria Tzelepi , Vasileios Mezaris

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word…

Computation and Language · Computer Science 2019-02-22 Hainan Xu , Shuoyang Ding , Shinji Watanabe

In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes. It is a two-stage training approach that first uses a…

Computer Vision and Pattern Recognition · Computer Science 2022-07-29 Maria A. Bravo , Sudhanshu Mittal , Thomas Brox

This paper proposes a novel two-stage method for the classification of hyperspectral images. Pixel-wise classifiers, such as the classical support vector machine (SVM), consider spectral information only; therefore they would generate noisy…

Image and Video Processing · Electrical Eng. & Systems 2018-06-05 Raymond H. Chan , Kelvin K. Kan , Mila Nikolova , Robert J. Plemmons

This paper describes a novel method of live keyword spotting using a two-stage time delay neural network. The model is trained using transfer learning: initial training with phone targets from a large speech corpus is followed by training…

Audio and Speech Processing · Electrical Eng. & Systems 2018-08-29 Samuel Myer , Vikrant Singh Tomar