English
Related papers

Related papers: Focus on the present: a regularization method for …

200 papers

Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant…

Machine Learning · Computer Science 2022-07-18 Bowen Zhao , Huanlai Xing , Xinhan Wang , Fuhong Song , Zhiwen Xiao

Temporal sentence grounding aims to localize moments relevant to a language description. Recently, DETR-like approaches achieved notable progress by predicting the center and length of a target moment. However, they suffer from the issue of…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Pilhyeon Lee , Hyeran Byun

Connectionist Temporal Classification (CTC), a non-autoregressive training criterion, is widely used in online keyword spotting (KWS). However, existing CTC-based KWS decoding strategies either rely on Automatic Speech Recognition (ASR),…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-25 Yu Xi , Haoyu Li , Xiaoyu Gu , Hao Li , Yidi Jiang , Kai Yu

For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-27 Qiujia Li , David Qiu , Yu Zhang , Bo Li , Yanzhang He , Philip C. Woodland , Liangliang Cao , Trevor Strohman

Multi-head attention mechanism is capable of learning various representations from sequential data while paying attention to different subsequences, e.g., word-pieces or syllables in a spoken word. From the subsequences, it retrieves richer…

Machine Learning · Computer Science 2019-10-11 Mingu Lee , Jinkyu Lee , Hye Jin Jang , Byeonggeun Kim , Wonil Chang , Kyuwoong Hwang

Large Language Models (LLMs) are strong decoders for Serialized Output Training (SOT) in two-talker Automatic Speech Recognition (ASR), yet their performance degrades substantially in challenging conditions such as three-talker mixtures. A…

Sound · Computer Science 2026-03-31 Hao Shi , Yuan Gao , Xugang Lu , Tatsuya Kawahara

In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Simpenzwe Honore Leandre , Natenaile Asmamaw Shiferaw , Dillip Rout

Long-form speech recognition is an application area of increasing research focus. ASR models based on multi-head attention (MHA) are ill-suited to long-form ASR because of their quadratic complexity in sequence length. We build on recent…

Computation and Language · Computer Science 2025-06-25 Martin Ratajczak , Jean-Philippe Robichaud , Jennifer Drexler Fox

Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-16 Minglun Han , Ye Bai , Chen Shen , Youjia Huang , Mingkun Huang , Zehua Lin , Linhao Dong , Lu Lu , Yuxuan Wang

End-To-End speech recognition have become increasingly popular in mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treatment for the acoustic…

Computation and Language · Computer Science 2018-05-15 Wei Zou , Dongwei Jiang , Shuaijiang Zhao , Xiangang Li

Scene text recognition has been an important, active research topic in computer vision for years. Previous approaches mainly consider text as 1D signals and cast scene text recognition as a sequence prediction problem, by feat of CTC or…

Computer Vision and Pattern Recognition · Computer Science 2019-07-24 Zhaoyi Wan , Fengming Xie , Yibo Liu , Xiang Bai , Cong Yao

End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, to improve the recognition accuracy on such rare words, is to…

Computation and Language · Computer Science 2021-11-08 Feng-Ju Chang , Jing Liu , Martin Radfar , Athanasios Mouchtaris , Maurizio Omologo , Ariya Rastrow , Siegfried Kunzmann

In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunkwise attention (MoChA) and head-synchronous…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-14 Mohan Li , Shucong Zhang , Catalin Zorila , Rama Doddipatla

Attention-based sequence-to-sequence automatic speech recognition (ASR) requires a significant delay to recognize long utterances because the output is generated after receiving entire input sequences. Although several studies recently…

Computation and Language · Computer Science 2020-11-05 Sashi Novitasari , Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil the teacher's knowledge, we use an attention decoder that…

Computation and Language · Computer Science 2024-01-23 Michael Hentschel , Yuta Nishikawa , Tatsuya Komatsu , Yusuke Fujita

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

The Abstraction and Reasoning Corpus (ARC) is designed to assess generalization beyond pattern matching, requiring models to infer symbolic rules from very few examples. In this work, we present a transformer-based system that advances ARC…

Non-autoregressive (NAR) transformer models have achieved significantly inference speedup but at the cost of inferior accuracy compared to autoregressive (AR) models in automatic speech recognition (ASR). Most of the NAR transformers take a…

Sound · Computer Science 2021-04-19 Xingchen Song , Zhiyong Wu , Yiheng Huang , Chao Weng , Dan Su , Helen Meng

Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities. These models have recently shown promising results for modeling discrete sequences, but they are non-trivial…

Computation and Language · Computer Science 2018-06-19 Matthias Sperber , Jan Niehues , Graham Neubig , Sebastian Stüker , Alex Waibel

The recently proposed serialized output training (SOT) simplifies multi-talker automatic speech recognition (ASR) by generating speaker transcriptions separated by a special token. However, frequent speaker changes can make speaker change…

Sound · Computer Science 2023-10-06 Yuhao Liang , Fan Yu , Yangze Li , Pengcheng Guo , Shiliang Zhang , Qian Chen , Lei Xie