English
Related papers

Related papers: Who Needs Decoders? Efficient Estimation of Sequen…

200 papers

Diffusion Language Models (DLMs) are often advertised as enabling parallel token generation, yet practical fast DLMs frequently converge to left-to-right, autoregressive (AR)-like decoding dynamics. In contrast, genuinely non-AR generation…

Computation and Language · Computer Science 2026-03-02 Pengxiang Li , Dilxat Muhtar , Tianlong Chen , Lu Yin , Shiwei Liu

End-to-end automatic speech recognition (ASR) systems based on transformer architectures, such as Whisper, offer high transcription accuracy and robustness. However, their autoregressive decoding is computationally expensive, hence limiting…

Computation and Language · Computer Science 2025-07-30 Tuan Vu Ho , Hiroaki Kokubo , Masaaki Yamamoto , Yohei Kawaguchi

How do we perform efficient inference while retaining high translation quality? Existing neural machine translation models, such as Transformer, achieve high performance, but they decode words one by one, which is inefficient. Recent…

Computation and Language · Computer Science 2021-10-15 Chenyang Huang , Hao Zhou , Osmar R. Zaïane , Lili Mou , Lei Li

In this paper, we propose methods for improving the modeling performance of a Transformer-based non-autoregressive text-to-speech (TNA-TTS) model. Although the text encoder and audio decoder handle different types and lengths of data (i.e.,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-30 Jae-Sung Bae , Tae-Jun Bak , Young-Sun Joo , Hoon-Young Cho

This article describes an efficient end-to-end speech translation (E2E-ST) framework based on non-autoregressive (NAR) models. End-to-end speech translation models have several advantages over traditional cascade systems such as inference…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-10 Hirofumi Inaguma , Yosuke Higuchi , Kevin Duh , Tatsuya Kawahara , Shinji Watanabe

The field of image synthesis is currently flourishing due to the advancements in diffusion models. While diffusion models have been successful, their computational intensity has prompted the pursuit of more efficient alternatives. As a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Zanlin Ni , Yulin Wang , Renping Zhou , Jiayi Guo , Jinyi Hu , Zhiyuan Liu , Shiji Song , Yuan Yao , Gao Huang

Visual autoregressive models typically adhere to a raster-order ``next-token prediction" paradigm, which overlooks the spatial and temporal locality inherent in visual content. Specifically, visual tokens exhibit significantly stronger…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Yefei He , Yuanyu He , Shaoxuan He , Feng Chen , Hong Zhou , Kaipeng Zhang , Bohan Zhuang

Autoregressive (AR) models, common in sequence generation, are limited in many biological tasks such as de novo peptide sequencing and protein modeling by their unidirectional nature, failing to capture crucial global bidirectional token…

Machine Learning · Computer Science 2025-12-12 Xiang Zhang , Jiaqi Wei , Zijie Qiu , Sheng Xu , Zhi Jin , ZhiQiang Gao , Nanqing Dong , Siqi Sun

Non-autoregressive (NAR) models can generate sentences with less computation than autoregressive models but sacrifice generation quality. Previous studies addressed this issue through iterative decoding. This study proposes using nearest…

Computation and Language · Computer Science 2022-08-29 Ayana Niwa , Sho Takase , Naoaki Okazaki

Non-autoregressive automatic speech recognition (ASR) has become a mainstream of ASR modeling because of its fast decoding speed and satisfactory result. To further boost the performance, relaxing the conditional independence assumption and…

Computation and Language · Computer Science 2023-05-19 Chong-En Lin , Kuan-Yu Chen

Non-autoregressive translation (NAT) models achieve comparable performance and superior speed compared to auto-regressive translation (AT) models in the context of sentence-level machine translation (MT). However, their abilities are…

Computation and Language · Computer Science 2023-12-12 Guangsheng Bao , Zhiyang Teng , Hao Zhou , Jianhao Yan , Yue Zhang

Discrete normalizing flows are promising generative models with advantages such as analytical log-likelihood computation and end-to-end training. However, the architectural constraints to ensure invertibility and tractable Jacobian…

Machine Learning · Computer Science 2026-05-06 Jiaru Zhang , Juanwu Lu , Xiaoyu Wu , Ziran Wang , Ruqi Zhang

Sequence-to-sequence vision-language models are showing promise, but their applicability is limited by their inference latency due to their autoregressive way of generating predictions. We propose a parallel decoding sequence-to-sequence…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Kunyu Shi , Qi Dong , Luis Goncalves , Zhuowen Tu , Stefano Soatto

Existing sentence ordering approaches generally employ encoder-decoder frameworks with the pointer net to recover the coherence by recurrently predicting each sentence step-by-step. Such an autoregressive manner only leverages unilateral…

Computation and Language · Computer Science 2023-10-20 Yi Bin , Wenhao Shi , Bin Ji , Jipeng Zhang , Yujuan Ding , Yang Yang

Non-autoregressive (nAR) models for machine translation (MT) manifest superior decoding speed when compared to autoregressive (AR) models, at the expense of impaired fluency of their outputs. We improve the fluency of a nAR model with…

Computation and Language · Computer Science 2020-04-08 Zdeněk Kasner , Jindřich Libovický , Jindřich Helcl

Non-autoregressive (NAR) automatic speech recognition (ASR) models predict tokens independently and simultaneously, bringing high inference speed. However, there is still a gap in the accuracy of the NAR models compared to the…

Sound · Computer Science 2025-01-10 Ziyang Zhuang , Chenfeng Miao , Kun Zou , Ming Fang , Tao Wei , Zijian Li , Ning Cheng , Wei Hu , Shaojun Wang , Jing Xiao

An effective recipe for building seq2seq, non-autoregressive, task-oriented parsers to map utterances to semantic frames proceeds in three steps: encoding an utterance $x$, predicting a frame's length |y|, and decoding a |y|-sized frame…

Computation and Language · Computer Science 2021-09-16 Akshat Shrivastava , Pierce Chuang , Arun Babu , Shrey Desai , Abhinav Arora , Alexander Zotov , Ahmed Aly

Non-autoregressive (NAR) transformer models have been studied intensively in automatic speech recognition (ASR), and a substantial part of NAR transformer models is to use the casual mask to limit token dependencies. However, the casual…

Computation and Language · Computer Science 2021-09-15 Chuan-Fei Zhang , Yan Liu , Tian-Hao Zhang , Song-Lu Chen , Feng Chen , Xu-Cheng Yin

In real-world systems, scaling has been critical for improving the translation quality in autoregressive translation (AT), which however has not been well studied for non-autoregressive translation (NAT). In this work, we bridge the gap by…

Computation and Language · Computer Science 2023-06-05 Zhihao Wang , Longyue Wang , Jinsong Su , Junfeng Yao , Zhaopeng Tu

Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these two types of speech representations compare when used as…

Sound · Computer Science 2026-03-12 Sofiene Kammoun , Xavier Alameda-Pineda , Simon Leglaive