English
Related papers

Related papers: Spike-Triggered Non-Autoregressive Transformer for…

200 papers

Non-autoregressive neural machine translation (NAT) predicts the entire target sequence simultaneously and significantly accelerates inference process. However, NAT discards the dependency information in a sentence, and thus inevitably…

Computation and Language · Computer Science 2020-06-11 Qiu Ran , Yankai Lin , Peng Li , Jie Zhou

Non-autoregressive (NAR) machine translation has recently achieved significant improvements, and now outperforms autoregressive (AR) models on some benchmarks, providing an efficient alternative to AR inference. However, while AR…

Computation and Language · Computer Science 2021-12-17 Sweta Agrawal , Julia Kreutzer , Colin Cherry

Spiking transformers achieve competitive accuracy with conventional transformers while offering $38$-$57\times$ energy efficiency on neuromorphic hardware, yet no theoretical framework guides their design. This paper establishes the first…

Machine Learning · Computer Science 2026-04-20 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability. However, it is challenging to adapt it with text-only data. Factorized neural transducer (FNT) model was proposed to…

Computation and Language · Computer Science 2023-02-24 Rui Zhao , Jian Xue , Partha Parthasarathy , Veljko Miljanic , Jinyu Li

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

Previous studies demonstrated that a dynamic phone-informed compression of the input audio is beneficial for speech translation (ST). However, they required a dedicated model for phone recognition and did not test this solution for direct…

Computation and Language · Computer Science 2021-10-15 Marco Gaido , Mauro Cettolo , Matteo Negri , Marco Turchi

Modern autoregressive speech synthesis models leveraging language models have demonstrated remarkable performance. However, the sequential nature of next token prediction in these models leads to significant latency, hindering their…

Sound · Computer Science 2025-06-04 Zijian Lin , Yang Zhang , Yougen Yuan , Yuming Yan , Jinjiang Liu , Zhiyong Wu , Pengfei Hu , Qun Yu

To translate speech for automatic dubbing, machine translation needs to be isochronous, i.e. translated speech needs to be aligned with the source in terms of speech durations. We introduce target factors in a transformer model to predict…

Computation and Language · Computer Science 2023-05-23 Proyag Pal , Brian Thompson , Yogesh Virkar , Prashant Mathur , Alexandra Chronopoulou , Marcello Federico

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent…

Computation and Language · Computer Science 2022-10-11 Chenze Shao , Yang Feng

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

In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discrete components such as…

Machine Learning · Computer Science 2021-08-30 Chanwoo Kim , Dhananjaya Gowda , Dongsoo Lee , Jiyeon Kim , Ankur Kumar , Sungsoo Kim , Abhinav Garg , Changwoo Han

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

Computation and Language · Computer Science 2020-03-25 Alex Bie , Bharat Venkitesh , Joao Monteiro , Md. Akmal Haidar , Mehdi Rezagholizadeh

End-to-end approaches have drawn much attention recently for significantly simplifying the construction of an automatic speech recognition (ASR) system. RNN transducer (RNN-T) is one of the popular end-to-end methods. Previous studies have…

Computation and Language · Computer Science 2019-04-24 Senmao Wang , Pan Zhou , Wei Chen , Jia Jia , Lei Xie

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Audio and Speech Processing · Electrical Eng. & Systems 2018-08-22 Shruti Palaskar , Florian Metze

To alleviate the data scarcity problem in End-to-end speech translation (ST), pre-training on data for speech recognition and machine translation is considered as an important technique. However, the modality gap between speech and text…

Computation and Language · Computer Science 2022-12-20 Xingshan Zeng , Liangyou Li , Qun Liu

In this paper, we present a novel modeling method for single-channel multi-talker overlapped automatic speech recognition (ASR) systems. Fully neural network based end-to-end models have dramatically improved the performance of multi-taker…

Computation and Language · Computer Science 2021-07-06 Ryo Masumura , Daiki Okamura , Naoki Makishima , Mana Ihori , Akihiko Takashima , Tomohiro Tanaka , Shota Orihashi

This paper integrates a voice activity detection (VAD) function with end-to-end automatic speech recognition toward an online speech interface and transcribing very long audio recordings. We focus on connectionist temporal classification…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-16 Takenori Yoshimura , Tomoki Hayashi , Kazuya Takeda , Shinji Watanabe

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

Deep neural network models for speech recognition have achieved great success recently, but they can learn incorrect associations between the target and nuisance factors of speech (e.g., speaker identities, background noise, etc.), which…

Computation and Language · Computer Science 2019-07-09 I-Hung Hsu , Ayush Jaiswal , Premkumar Natarajan

A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers…

Computation and Language · Computer Science 2020-11-25 Parnia Bahar , Tobias Bieschke , Ralf Schlüter , Hermann Ney