English
Related papers

Related papers: Blank Collapse: Compressing CTC emission for the f…

200 papers

An inferior performance of the streaming automatic speech recognition models versus non-streaming model is frequently seen due to the absence of future context. In order to improve the performance of the streaming model and reduce the…

Sound · Computer Science 2022-03-30 Jingyu Sun , Guiping Zhong , Dinghao Zhou , Baoxiang Li

This work presents a novel trie (prefix-tree)-based parallel decoding method that addresses the memory inefficiency of batch-based beam search. By sharing a single KV cache across beams with common prefixes, our approach dramatically…

Computation and Language · Computer Science 2025-09-23 Brian J Chan , MaoXun Huang , Jui-Hung Cheng , Chao-Ting Chen , Hen-Hsen Huang

Recent visual-text compression (VTC) methods, typified by DeepSeek-OCR, report impressive high token compression ratios for long-context modeling tasks by leveraging text-to-image rendering. However, existing evaluation protocols heavily…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yonghan Gao , Zehong Chen , Lijian Xu , Jingzhi Chen , Jingwei Guan , Xingyu Zeng

Cell detection is the task of detecting the approximate positions of cell centroids from microscopy images. Recently, convolutional neural network-based approaches have achieved promising performance. However, these methods require a…

Computer Vision and Pattern Recognition · Computer Science 2021-07-20 Kazuya Nishimura , Hyeonwoo Cho , Ryoma Bise

Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. Here, we focus on…

Computation and Language · Computer Science 2017-05-08 Jacob Devlin

End-to-end models that condition the output label sequence on all previously predicted labels have emerged as popular alternatives to conventional systems for automatic speech recognition (ASR). Since unique label histories correspond to…

Computation and Language · Computer Science 2020-12-15 Rohit Prabhavalkar , Yanzhang He , David Rybach , Sean Campbell , Arun Narayanan , Trevor Strohman , Tara N. Sainath

State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding…

Computation and Language · Computer Science 2020-07-23 Haim Dubossarsky , Simon Hengchen , Nina Tahmasebi , Dominik Schlechtweg

We present two solutions to sentence-level SLR. Sentence-level SLR required mapping videos of sign language sentences to sequences of gloss labels. Connectionist Temporal Classification (CTC) has been used as the classifier level of both…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Atra Akandeh

In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstraction gap between input acoustic signals and output linguistic…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-09 Yosuke Higuchi , Keita Karube , Tetsuji Ogawa , Tetsunori Kobayashi

Scaling large language models (LLMs) has driven significant advancements, yet it faces diminishing returns and escalating energy demands. This work explores how test-time compute (TTC) can serve as an energy-efficient complement to…

Machine Learning · Computer Science 2025-11-11 Yunho Jin , Gu-Yeon Wei , David Brooks

End-to-end Automatic Speech Recognition (ASR) systems based on neural networks have seen large improvements in recent years. The availability of large scale hand-labeled datasets and sufficient computing resources made it possible to train…

Computer Vision and Pattern Recognition · Computer Science 2023-01-05 Maxime Burchi , Radu Timofte

Unlabeled data is often used to learn representations which can be used to supplement baseline features in a supervised learner. For example, for text applications where the words lie in a very high dimensional space (the size of the…

Computation and Language · Computer Science 2012-07-03 Paramveer Dhillon , Jordan Rodu , Dean Foster , Lyle Ungar

Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-06 Ludwig Kürzinger , Dominik Winkelbauer , Lujun Li , Tobias Watzel , Gerhard Rigoll

Multi-Label Text Classification (MLTC) aims to assign the most relevant labels to each given text. Existing methods demonstrate that label dependency can help to improve the model's performance. However, the introduction of label dependency…

Computation and Language · Computer Science 2023-10-12 Caoyun Fan , Wenqing Chen , Jidong Tian , Yitian Li , Hao He , Yaohui Jin

Recent advances in segmentation-free keyword spotting treat this problem w.r.t. an object detection paradigm and borrow from state-of-the-art detection systems to simultaneously propose a word bounding box proposal mechanism and compute a…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 George Retsinas , Giorgos Sfikas , Christophoros Nikou

Recently, Chinese Spell Checking(CSC), a task to detect erroneous characters in a sentence and correct them, has attracted extensive interest because of its wide applications in various NLP tasks. Most of the existing methods have utilized…

Computation and Language · Computer Science 2023-05-08 Haiyun Yang

Captcha are widely used to secure systems from automatic responses by distinguishing computer responses from human responses. Text, audio, video, picture picture-based Optical Character Recognition (OCR) are used for creating captcha.…

Computer Vision and Pattern Recognition · Computer Science 2024-02-09 Vaibhav Khatavkar , Makarand Velankar , Sneha Petkar

The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we study how to reduce…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-09 Maxime Burchi , Valentin Vielzeuf

The connectionist temporal classification (CTC) enables end-to-end sequence learning by maximizing the probability of correctly recognizing sequences during training. The outputs of a CTC-trained model tend to form a series of spikes…

Computer Vision and Pattern Recognition · Computer Science 2020-07-08 Hongzhu Li , Weiqiang Wang

There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker…

Sound · Computer Science 2019-05-14 Achintya kr. Sarkar , Zheng-Hua Tan , Hao Tang , Suwon Shon , James Glass