English
Related papers

Related papers: Efficient Wait-k Models for Simultaneous Machine T…

200 papers

Training monolingual language models for low and mid-resource languages is made challenging by limited and often inadequate pretraining data. In this study, we propose a novel model conversion strategy to address this issue, adapting…

Computation and Language · Computer Science 2023-10-06 François Remy , Pieter Delobelle , Bettina Berendt , Kris Demuynck , Thomas Demeester

While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible. Towards a better understanding of this phenomenon, our work…

Machine Learning · Computer Science 2024-02-13 Valentino Maiorca , Luca Moschella , Antonio Norelli , Marco Fumero , Francesco Locatello , Emanuele Rodolà

Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models (LLMs) have showcased strong capabilities in offline translation tasks, applying them to…

Computation and Language · Computer Science 2025-04-17 Biao Fu , Donglei Yu , Minpeng Liao , Chengxi Li , Yidong Chen , Kai Fan , Xiaodong Shi

Recent work in multilingual translation advances translation quality surpassing bilingual baselines using deep transformer models with increased capacity. However, the extra latency and memory costs introduced by this approach may make it…

Computation and Language · Computer Science 2022-06-07 Xiang Kong , Adithya Renduchintala , James Cross , Yuqing Tang , Jiatao Gu , Xian Li

The Transformer model has revolutionized Natural Language Processing tasks such as Neural Machine Translation, and many efforts have been made to study the Transformer architecture, which increased its efficiency and accuracy. One potential…

Computation and Language · Computer Science 2023-08-17 Daniela N. Rim , Kimera Richard , Heeyoul Choi

Decoder-only transformers have become the standard architecture for large language models (LLMs) due to their strong performance. Recent studies suggest that, in pre-trained LLMs, early, middle, and late layers may serve distinct roles:…

Computation and Language · Computer Science 2025-10-15 Xuan Luo , Weizhi Wang , Xifeng Yan

State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens. The sequential nature of this generation process causes fundamental latency in…

Computation and Language · Computer Science 2020-07-01 Jungo Kasai , James Cross , Marjan Ghazvininejad , Jiatao Gu

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

Simultaneous machine translation, which aims at a real-time translation, is useful in many live scenarios but very challenging due to the trade-off between accuracy and latency. To achieve the balance for both, the model needs to wait for…

Computation and Language · Computer Science 2023-03-22 Lei Lin , Shuangtao Li , Xiaodong Shi

Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this…

Computation and Language · Computer Science 2024-09-27 Belen Alastruey , Gerard I. Gállego , Marta R. Costa-jussà

Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length…

Computation and Language · Computer Science 2014-10-08 Kyunghyun Cho , Bart van Merrienboer , Dzmitry Bahdanau , Yoshua Bengio

There have been significant efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation (NMT); meanwhile, the decoder remains largely unexamined despite its critical role. During…

Computation and Language · Computer Science 2020-10-07 Yilin Yang , Longyue Wang , Shuming Shi , Prasad Tadepalli , Stefan Lee , Zhaopeng Tu

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence…

Computation and Language · Computer Science 2020-11-03 Xutai Ma , Yongqiang Wang , Mohammad Javad Dousti , Philipp Koehn , Juan Pino

Speech generation models based on large language models (LLMs) typically operate on discrete acoustic codes, which differ fundamentally from text tokens due to their multicodebook structure. At each timestep, models must predict N codebook…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-26 Roy Fejgin , Paarth Neekhara , Xuesong Yang , Edresson Casanova , Ryan Langman , Jaehyeon Kim , Subhankar Ghosh , Shehzeen Hussain , Jason Li

Simultaneous machine translation (SiMT) generates translation while reading the whole source sentence. However, existing SiMT models are typically trained using the same reference disregarding the varying amounts of available source…

Computation and Language · Computer Science 2023-10-27 Shoutao Guo , Shaolei Zhang , Yang Feng

Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks. Nonetheless, the capabilities of these encoders in low-resource settings are yet to be thoroughly…

Computation and Language · Computer Science 2023-05-30 Hao Yang , Jinming Zhao , Gholamreza Haffari , Ehsan Shareghi

Speech-to-text translation (ST), which directly translates the source language speech to the target language text, has attracted intensive attention recently. However, the combination of speech recognition and machine translation in a…

Computation and Language · Computer Science 2022-04-18 Qianqian Dong , Mingxuan Wang , Hao Zhou , Shuang Xu , Bo Xu , Lei Li

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Computation and Language · Computer Science 2025-09-23 Alok N. Shah , Khush Gupta , Keshav Ramji , Pratik Chaudhari

Simultaneous speech-to-text translation is widely useful in many scenarios. The conventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra latency. To alleviate…

Computation and Language · Computer Science 2021-06-15 Junkun Chen , Mingbo Ma , Renjie Zheng , Liang Huang

Decoding in a Transformer based language model is inherently sequential as a token's embedding needs to pass through all the layers in the network before the generation of the next token can begin. In this work, we propose a new…

Machine Learning · Computer Science 2025-08-27 Dylan Cutler , Arun Kandoor , Nishanth Dikkala , Nikunj Saunshi , Xin Wang , Rina Panigrahy