English
Related papers

Related papers: Exponential Moving Average Model in Parallel Speec…

200 papers

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…

Computation and Language · Computer Science 2017-03-22 Xu Tian , Jun Zhang , Zejun Ma , Yi He , Juan Wei , Peihao Wu , Wenchang Situ , Shuai Li , Yang Zhang

Parallelization framework has become a necessity to speed up the training of deep neural networks (DNN) recently. Such framework typically employs the Model Average approach, denoted as MA-DNN, in which parallel workers conduct respective…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-07-19 Shizhao Sun , Wei Chen , Jiang Bian , Xiaoguang Liu , Tie-Yan Liu

In this work we apply model averaging to parallel training of deep neural network (DNN). Parallelization is done in a model averaging manner. Data is partitioned and distributed to different nodes for local model updates, and model…

Machine Learning · Computer Science 2018-07-03 Hang Su , Haoyu Chen

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed approach uses a teacher model which is updated as the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-28 Vimal Manohar , Tatiana Likhomanenko , Qiantong Xu , Wei-Ning Hsu , Ronan Collobert , Yatharth Saraf , Geoffrey Zweig , Abdelrahman Mohamed

Exponential moving average (EMA) has recently gained significant popularity in training modern deep learning models, especially diffusion-based generative models. However, there have been few theoretical results explaining the effectiveness…

Machine Learning · Computer Science 2025-02-21 Xuheng Li , Quanquan Gu

Variational inference has had great success in scaling approximate Bayesian inference to big data by exploiting mini-batch training. To date, however, this strategy has been most applicable to models of independent data. We propose an…

Machine Learning · Statistics 2021-05-19 Tom Ryder , Dennis Prangle , Andrew Golightly , Isaac Matthews

We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to…

Sound · Computer Science 2018-05-03 Han Zhao , Shuayb Zarar , Ivan Tashev , Chin-Hui Lee

We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher based self- and semi-supervised learning techniques. Unlike the…

Machine Learning · Computer Science 2021-06-21 Zhaowei Cai , Avinash Ravichandran , Subhransu Maji , Charless Fowlkes , Zhuowen Tu , Stefano Soatto

This paper is the first study to apply deep mutual learning (DML) to end-to-end ASR models. In DML, multiple models are trained simultaneously and collaboratively by mimicking each other throughout the training process, which helps to…

Computation and Language · Computer Science 2021-02-17 Ryo Masumura , Mana Ihori , Akihiko Takashima , Tomohiro Tanaka , Takanori Ashihara

Deep neural network (DNN) based speech enhancement models have attracted extensive attention due to their promising performance. However, it is difficult to deploy a powerful DNN in real-time applications because of its high computational…

Sound · Computer Science 2022-07-25 Xiaohuai Le , Tong Lei , Kai Chen , Jing Lu

Exponential random graph models (ERGMs) are very flexible for modeling network formation but pose difficult estimation challenges due to their intractable normalizing constant. Existing methods, such as MCMC-MLE, rely on sequential…

Social and Information Networks · Computer Science 2025-02-05 Angelo Mele

Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Mandarin speech recognition task, a novel transformer…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-29 Li Fu , Xiaoxiao Li , Libo Zi

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation…

Machine Learning · Computer Science 2019-12-02 Julia El Zini , Yara Rizk , Mariette Awad

Distant speech recognition is a challenge, particularly due to the corruption of speech signals by reverberation caused by large distances between the speaker and microphone. In order to cope with a wide range of reverberations in…

Computation and Language · Computer Science 2016-08-18 Jeehye Lee , Myungin Lee , Joon-Hyuk Chang

Continual learning for automatic speech recognition (ASR) systems poses a challenge, especially with the need to avoid catastrophic forgetting while maintaining performance on previously learned tasks. This paper introduces a novel approach…

Computation and Language · Computer Science 2024-11-28 Geoffrey Tyndall , Kurniawati Azizah , Dipta Tanaya , Ayu Purwarianti , Dessi Puji Lestari , Sakriani Sakti

The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance…

Machine Learning · Computer Science 2021-03-25 Andrea Cossu , Antonio Carta , Davide Bacciu

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

We examine two different techniques for parameter averaging in GAN training. Moving Average (MA) computes the time-average of parameters, whereas Exponential Moving Average (EMA) computes an exponentially discounted sum. Whilst MA is known…

Deep learning models (DLMs) are state-of-the-art techniques in speech recognition. However, training good DLMs can be time consuming especially for production-size models and corpora. Although several parallel training algorithms have been…

Computation and Language · Computer Science 2018-12-06 Wenpeng Li , BinBin Zhang , Lei Xie , Dong Yu

Training machine learning models in parallel is an increasingly important workload. We accelerate distributed parallel training by designing a communication primitive that uses a programmable switch dataplane to execute a key step of the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-10-01 Amedeo Sapio , Marco Canini , Chen-Yu Ho , Jacob Nelson , Panos Kalnis , Changhoon Kim , Arvind Krishnamurthy , Masoud Moshref , Dan R. K. Ports , Peter Richtárik
‹ Prev 1 2 3 10 Next ›