English
Related papers

Related papers: Chunked Attention-based Encoder-Decoder Model for …

200 papers

The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach…

Computation and Language · Computer Science 2021-07-08 Belen Alastruey , Gerard I. Gállego , Marta R. Costa-jussà

Current speech enhancement (SE) research has largely neglected channel attention and spatial attention, and encoder-decoder architecture-based networks have not adequately considered how to provide efficient inputs to the intermediate…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-12 Junyu Wang

This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transformer ignoring the lookahead context. We propose to use…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-12 Yangyang Shi , Chunyang Wu , Dilin Wang , Alex Xiao , Jay Mahadeokar , Xiaohui Zhang , Chunxi Liu , Ke Li , Yuan Shangguan , Varun Nagaraja , Ozlem Kalinli , Mike Seltzer

We propose the Chunkwise Aligner, a novel architecture for streaming automatic speech recognition (ASR). While the Transducer is the standard model for streaming ASR, its training is costly due to the need to compute all possible…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-13 Wen Shen Teo , Takafumi Moriya , Masato Mimura

Although dominant in natural language processing, transformer-based models remain challenged by the task of long-sequence processing, because the computational cost of self-attention operations in transformers swells quadratically with the…

Computation and Language · Computer Science 2024-07-08 Jiawen Xie , Pengyu Cheng , Xiao Liang , Yong Dai , Nan Du

Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is a key issue to…

Computation and Language · Computer Science 2021-03-02 Xie Chen , Yu Wu , Zhenghao Wang , Shujie Liu , Jinyu Li

Transformer-based end-to-end (E2E) automatic speech recognition (ASR) systems have recently gained wide popularity, and are shown to outperform E2E models based on recurrent structures on a number of ASR tasks. However, like other E2E…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-30 Mohan Li , Catalin Zorila , Rama Doddipatla

Transformer-based encoder-decoder models produce a fused token-wise representation after every encoder layer. We investigate the effects of allowing the encoder to preserve and explore alternative hypotheses, combined at the end of the…

Computation and Language · Computer Science 2021-07-23 Mikhail Burtsev , Anna Rumshisky

State-of-the-art audio captioning methods typically use the encoder-decoder structure with pretrained audio neural networks (PANNs) as encoders for feature extraction. However, the convolution operation used in PANNs is limited in capturing…

Sound · Computer Science 2023-04-11 Feiyang Xiao , Jian Guan , Qiaoxi Zhu , Wenwu Wang

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Computation and Language · Computer Science 2024-05-06 Vahid Noroozi , Somshubra Majumdar , Ankur Kumar , Jagadeesh Balam , Boris Ginsburg

Selective auditory attention decoding aims to identify the speaker of interest from listeners' neural signals, such as electroencephalography (EEG), in the presence of multiple concurrent speakers. Most existing methods operate at the…

Signal Processing · Electrical Eng. & Systems 2026-02-17 Yuanyuan Yao , Simon Geirnaert , Tinne Tuytelaars , Alexander Bertrand

Conventional automatic speech recognition (ASR) typically performs multi-level pattern recognition tasks that map the acoustic speech waveform into a hierarchy of speech units. But, it is widely known that information loss in the earlier…

Computation and Language · Computer Science 2017-09-25 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional…

Computation and Language · Computer Science 2021-04-13 Luyang Huang , Shuyang Cao , Nikolaus Parulian , Heng Ji , Lu Wang

Text-speech joint spoken language modeling (SLM) aims at natural and intelligent speech-based interactions, but developing such a system may suffer from modality mismatch: speech unit sequences are much longer than text tokens. Prior work…

Computation and Language · Computer Science 2026-03-16 Liang-Hsuan Tseng , Hung-yi Lee

Automatic Speech Recognition (ASR) using multiple microphone arrays has achieved great success in the far-field robustness. Taking advantage of all the information that each array shares and contributes is crucial in this task. Motivated by…

Computation and Language · Computer Science 2019-02-20 Xiaofei Wang , Ruizhi Li , Sri Harish Mallid , Takaaki Hori , Shinji Watanabe , Hynek Hermansky

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Computation and Language · Computer Science 2020-12-03 Iz Beltagy , Matthew E. Peters , Arman Cohan

Attention-based Encoder-Decoder has the effective architecture for neural machine translation (NMT), which typically relies on recurrent neural networks (RNN) to build the blocks that will be lately called by attentive reader during the…

Computation and Language · Computer Science 2017-12-07 Hao Xiong , Zhongjun He , Xiaoguang Hu , Hua Wu

In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational…

Computer Vision and Pattern Recognition · Computer Science 2025-02-14 Priyanka Mudgal , Feng Liu

Discrete diffusion models enable parallel token sampling for faster inference than autoregressive approaches. However, prior diffusion models use a decoder-only architecture, which requires sampling algorithms that invoke the full network…

Machine Learning · Computer Science 2025-10-28 Marianne Arriola , Yair Schiff , Hao Phung , Aaron Gokaslan , Volodymyr Kuleshov

This paper develops a novel encoder-decoder deep network architecture which exploits the several contextual frames of 2D+t sequential images in a sliding window centered at current frame to segment 2D vessel masks from the current frame.…

Computer Vision and Pattern Recognition · Computer Science 2021-02-11 Dongdong Hao , Song Ding , Linwei Qiu , Yisong Lv , Baowei Fei , Yueqi Zhu , Binjie Qin