English
Related papers

Related papers: Training and Inference Efficiency of Encoder-Decod…

200 papers

Compute scaling for language model (LM) pretraining has outpaced the growth of human-written texts, leading to concerns that data will become the bottleneck to LM scaling. To continue scaling pretraining in this data-constrained regime, we…

Machine Learning · Computer Science 2025-09-30 Yangjun Ruan , Neil Band , Chris J. Maddison , Tatsunori Hashimoto

Large language models (LLMs) often face a bottleneck in inference speed due to their reliance on auto-regressive decoding. Recently, parallel decoding has shown significant promise in enhancing inference efficiency. However, we have…

Computation and Language · Computer Science 2024-10-18 Yuxuan Liu , Wenyuan Li , Laizhong Cui , Hailiang Yang

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…

Computation and Language · Computer Science 2022-04-22 Nils-Philipp Wynands , Wilfried Michel , Jan Rosendahl , Ralf Schlüter , Hermann Ney

Model selection in Gaussian processes scales prohibitively with the size of the training dataset, both in time and memory. While many approximations exist, all incur inevitable approximation error. Recent work accounts for this error in the…

Machine Learning · Computer Science 2025-07-08 Jonathan Wenger , Kaiwen Wu , Philipp Hennig , Jacob R. Gardner , Geoff Pleiss , John P. Cunningham

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network. In this paper, we present theoretical analyses…

Machine Learning · Computer Science 2025-02-17 Hikaru Umeda , Hideaki Iiduka

The multi-stream paradigm of audio processing, in which several sources are simultaneously considered, has been an active research area for information fusion. Our previous study offered a promising direction within end-to-end automatic…

Computation and Language · Computer Science 2019-10-24 Ruizhi Li , Gregory Sell , Xiaofei Wang , Shinji Watanabe , Hynek Hermansky

Encoder-decoder models provide a generic architecture for sequence-to-sequence tasks such as speech recognition and translation. While offline systems are often evaluated on quality metrics like word error rates (WER) and BLEU, latency is…

Computation and Language · Computer Science 2020-10-14 Danni Liu , Gerasimos Spanakis , Jan Niehues

Encoder-decoder foundation models have displayed state-of-the-art performance on a range of autoregressive sequence tasks. This paper proposes a simple and lightweight modification to such systems to control the behaviour according to a…

Computation and Language · Computer Science 2024-05-06 Yassir Fathullah , Mark J. F. Gales

For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchronous problem between the encoding and decoding makes these…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-25 Zhengkun Tian , Jiangyan Yi , Ye Bai , Jianhua Tao , Shuai Zhang , Zhengqi Wen

Sequence transducers, such as the RNN-T and the Conformer-T, are one of the most promising models of end-to-end speech recognition, especially in streaming scenarios where both latency and accuracy are important. Although various methods,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-07 Yusuke Shinohara , Shinji Watanabe

Recently, the end-to-end training approach for neural beamformer-supported multi-channel ASR has shown its effectiveness in multi-channel speech recognition. However, the integration of multiple modules makes it more difficult to perform…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-07 Keyu An , Zhijian Ou

Recent advances in Transformers have come with a huge requirement on computing resources, highlighting the importance of developing efficient training techniques to make Transformer training faster, at lower cost, and to higher accuracy by…

Machine Learning · Computer Science 2023-05-05 Bohan Zhuang , Jing Liu , Zizheng Pan , Haoyu He , Yuetian Weng , Chunhua Shen

Training Transformer language models is expensive, as performance typically improves with increasing dataset size and computational budget. Although scaling laws describe this trend at large scale, their implications in controlled,…

As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by caching and reusing model outputs at uniformly…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Feng Liu , Shiwei Zhang , Xiaofeng Wang , Yujie Wei , Haonan Qiu , Yuzhong Zhao , Yingya Zhang , Qixiang Ye , Fang Wan

Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. However, with the progressive improvements in deep learning models, their number of…

Machine Learning · Computer Science 2024-04-17 Gaurav Menghani

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…

Computation and Language · Computer Science 2018-06-19 Sameer Bansal , Herman Kamper , Karen Livescu , Adam Lopez , Sharon Goldwater

Large language models (LLMs) have become proficient at solving a wide variety of tasks, including those involving multi-modal inputs. In particular, instantiating an LLM (such as LLaMA) with a speech encoder and training it on paired data…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-13 Desh Raj , Gil Keren , Junteng Jia , Jay Mahadeokar , Ozlem Kalinli

Retrieval-augmented language models have demonstrated performance comparable to much larger models while requiring fewer computational resources. The effectiveness of these models crucially depends on the overlap between query and retrieved…

Computation and Language · Computer Science 2025-05-21 Ehsan Doostmohammadi , Marco Kuhlmann

As recurrent neural networks become larger and deeper, training times for single networks are rising into weeks or even months. As such there is a significant incentive to improve the performance and scalability of these networks. While…

Machine Learning · Computer Science 2016-04-08 Jeremy Appleyard , Tomas Kocisky , Phil Blunsom

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…

Machine Learning · Computer Science 2023-01-25 Muralidhar Andoorveedu , Zhanda Zhu , Bojian Zheng , Gennady Pekhimenko