English
Related papers

Related papers: Pruned RNN-T for fast, memory-efficient ASR traini…

200 papers

In Machine Learning, Artificial Neural Networks (ANNs) are a very powerful tool, broadly used in many applications. Often, the selected (deep) architectures include many layers, and therefore a large amount of parameters, which makes…

Machine Learning · Computer Science 2022-06-29 Matteo Cacciola , Antonio Frangioni , Xinlin Li , Andrea Lodi

This article describes a density ratio approach to integrating external Language Models (LMs) into end-to-end models for Automatic Speech Recognition (ASR). Applied to a Recurrent Neural Network Transducer (RNN-T) ASR model trained on a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-02 Erik McDermott , Hasim Sak , Ehsan Variani

Recently, self-attention-based transformers and conformers have been introduced as alternatives to RNNs for ASR acoustic modeling. Nevertheless, the full-sequence attention mechanism is non-streamable and computationally expensive, thus…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-27 Keyu An , Shiliang Zhang

Neural networks achieve state-of-the-art performance in image classification, speech recognition, scientific analysis and many more application areas. Due to the high computational complexity and memory footprint of neural networks, various…

Hardware Architecture · Computer Science 2025-04-21 Benjamin Ramhorst , Vladimir Loncar , George A. Constantinides

A typical deep neural network (DNN) has a large number of trainable parameters. Choosing a network with proper capacity is challenging and generally a larger network with excessive capacity is trained. Pruning is an established approach to…

Neural and Evolutionary Computing · Computer Science 2021-03-01 Hojjat Salehinejad , Shahrokh Valaee

Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective…

Machine Learning · Computer Science 2022-09-15 Rongmei Lin , Yonghui Xiao , Tien-Ju Yang , Ding Zhao , Li Xiong , Giovanni Motta , Françoise Beaufays

In the last decade, Convolutional Neural Network with a multi-layer architecture has advanced rapidly. However, training its complex network is very space-consuming, since a lot of intermediate data are preserved across layers, especially…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-01-23 Zhigang Wang , Hangyu Yang , Ning Wang , Chuanfei Xu , Jie Nie , Zhiqiang Wei , Yu Gu , Ge Yu

Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs). However, large RNNs limit practical deployment in hearing aid hardware (HW) form-factors, which are battery…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-15 Igor Fedorov , Marko Stamenovic , Carl Jensen , Li-Chia Yang , Ari Mandell , Yiming Gan , Matthew Mattina , Paul N. Whatmough

In recent years, Long Short-Term Memory (LSTM) has become a popular choice for speech separation and speech enhancement task. The capability of LSTM network can be enhanced by widening and adding more layers. However, this would introduce…

Sound · Computer Science 2018-12-27 Suman Samui , Indrajit Chakrabarti , Soumya K. Ghosh

Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of…

Machine Learning · Computer Science 2019-12-24 Fu-Ming Guo , Sijia Liu , Finlay S. Mungall , Xue Lin , Yanzhi Wang

Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields. Previous work essentially improves the model performance by widening or…

Computer Vision and Pattern Recognition · Computer Science 2024-03-01 Zhifeng Ma , Hao Zhang , Jie Liu

RNN-T models have gained popularity in the literature and in commercial systems because of their competitiveness and capability of operating in online streaming mode. In this work, we conduct an extensive study comparing several prediction…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-30 Dario Albesano , Jesús Andrés-Ferrer , Nicola Ferri , Puming Zhan

Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural…

Machine Learning · Computer Science 2019-07-02 Jonathan Frankle , David Bau

Despite deep recurrent neural networks (RNNs) demonstrate strong performance in text classification, training RNN models are often expensive and requires an extensive collection of annotated data which may not be available. To overcome the…

Computation and Language · Computer Science 2018-10-02 Wasi Uddin Ahmad , Xueying Bai , Nanyun Peng , Kai-Wei Chang

The Outstanding performance and growing size of Large Language Models has led to increased attention in parameter efficient learning. The two predominant approaches are Adapters and Pruning. Adapters are to freeze the model and give it a…

Computation and Language · Computer Science 2023-04-07 Guorun Wang , Jun Yang , Yaoru Sun

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…

Neural and Evolutionary Computing · Computer Science 2013-03-26 Alex Graves , Abdel-rahman Mohamed , Geoffrey Hinton

End-to-end (E2E) models fold the acoustic, pronunciation and language models of a conventional speech recognition model into one neural network with a much smaller number of parameters than a conventional ASR system, thus making it suitable…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-14 Bo Li , Shuo-yiin Chang , Tara N. Sainath , Ruoming Pang , Yanzhang He , Trevor Strohman , Yonghui Wu

Pruning methods have shown to be effective at reducing the size of deep neural networks while keeping accuracy almost intact. Among the most effective methods are those that prune a network while training it with a sparsity prior loss and…

Neural and Evolutionary Computing · Computer Science 2019-12-20 Carl Lemaire , Andrew Achkar , Pierre-Marc Jodoin

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech…

Computation and Language · Computer Science 2018-11-05 Xiang Li , Haiyang Xue , Wei Chen , Yang Liu , Yang Feng , Qun Liu

Temporal graph neural networks (TGNNs) outperform regular GNNs by incorporating time information into graph-based operations. However, TGNNs adopt specialized models (e.g., TGN, TGAT, and APAN ) and require tailored training frameworks…

Machine Learning · Computer Science 2024-09-19 Qiang Huang , Xiao Yan , Xin Wang , Susie Xi Rao , Zhichao Han , Fangcheng Fu , Wentao Zhang , Jiawei Jiang
‹ Prev 1 8 9 10 Next ›