English
Related papers

Related papers: Dynamic Alignment Mask CTC: Improved Mask-CTC with…

200 papers

In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Mengyuan Tian , Qiyan Zhao , Yanan Wang , Da-Han Wang

Deep neural networks have shown exceptional performance in various tasks, but their lack of robustness, reliability, and tendency to be overconfident pose challenges for their deployment in safety-critical applications like autonomous…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Steven Landgraf , Markus Hillemann , Kira Wursthorn , Markus Ulrich

Consistency regularization (CR) improves the robustness and accuracy of Connectionist Temporal Classification (CTC) by ensuring predictions remain stable across input perturbations. In this work, we propose Align-Consistency, an extension…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-27 Wanting Huang , Weiran Wang

The cross entropy (CE) method is a model based search method to solve optimization problems where the objective function has minimal structure. The Monte-Carlo version of the CE method employs the naive sample averaging technique which is…

Artificial Intelligence · Computer Science 2018-02-01 Ajin George Joseph , Shalabh Bhatnagar

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end (E2E) Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-22 Ruizhi Li , Xiaofei Wang , Sri Harish Mallidi , Shinji Watanabe , Takaaki Hori , Hynek Hermansky

Non-autoregressive models greatly improve decoding speed over typical sequence-to-sequence models, but suffer from degraded performance. Infilling and iterative refinement models make up some of this gap by editing the outputs of a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-28 Ethan A. Chi , Julian Salazar , Katrin Kirchhoff

End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solution by selecting the most valuable samples for annotation.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-12 Jian Luo , Jianzong Wang , Ning Cheng , Jing Xiao

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by…

Machine Learning · Computer Science 2019-08-08 Hao-Yun Chen , Jhao-Hong Liang , Shih-Chieh Chang , Jia-Yu Pan , Yu-Ting Chen , Wei Wei , Da-Cheng Juan

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

Traditional empirical risk minimization (ERM) for semantic segmentation can disproportionately advantage or disadvantage certain target classes in favor of an (unfair but) improved overall performance. Inspired by the recently introduced…

Computer Vision and Pattern Recognition · Computer Science 2021-03-29 Attila Szabo , Hadi Jamali-Rad , Siva-Datta Mannava

Being one of the IR-NAT (Iterative-refinemennt-based NAT) frameworks, the Conditional Masked Language Model (CMLM) adopts the mask-predict paradigm to re-predict the masked low-confidence tokens. However, CMLM suffers from the data…

Computation and Language · Computer Science 2024-02-16 Xinran Chen , Sufeng Duan , Gongshen Liu

Speech enhancement algorithms based on deep learning have been improved in terms of speech intelligibility and perceptual quality greatly. Many methods focus on enhancing the amplitude spectrum while reconstructing speech using the mixture…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-10 Qinglong Li , Fei Gao , Haixin Guan , Kaichi Ma

It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the "multi-modality problem", including the…

Computation and Language · Computer Science 2022-07-12 Kexun Zhang , Rui Wang , Xu Tan , Junliang Guo , Yi Ren , Tao Qin , Tie-Yan Liu

Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing…

Computation and Language · Computer Science 2021-05-18 Chi Chen , Maosong Sun , Yang Liu

Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech recognition (ASR). This alignment is inherently structured and asymmetric: while multiple…

Computation and Language · Computer Science 2026-03-06 Xugang Lu , Peng Shen , Hisashi Kawai

Conventionally, the manner of articulations in speech signal are derived using discriminative signal processing techniques or deep learning approaches. However, training such complex systems involves feature extraction, phoneme force…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-06 Pradeep R , Sreenivasa Rao K

Existing training criteria in automatic speech recognition(ASR) permit the model to freely explore more than one time alignments between the feature and label sequences. In this paper, we use entropy to measure a model's uncertainty, i.e.…

Computation and Language · Computer Science 2022-12-26 Ehsan Variani , Ke Wu , David Rybach , Cyril Allauzen , Michael Riley

Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-23 Xiaofeng Ge , Jiangyu Han , Haixin Guan , Yanhua Long

In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the…

Sound · Computer Science 2021-12-30 Binbin Zhang , Di Wu , Zhuoyuan Yao , Xiong Wang , Fan Yu , Chao Yang , Liyong Guo , Yaguang Hu , Lei Xie , Xin Lei

Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a…

Computation and Language · Computer Science 2019-09-05 Marjan Ghazvininejad , Omer Levy , Yinhan Liu , Luke Zettlemoyer