English
Related papers

Related papers: Light Gated Recurrent Units for Speech Recognition

200 papers

Recurrent Neural Networks (RNNs) are used to learn representations in partially observable environments. For agents that learn online and continually interact with the environment, it is desirable to train RNNs with real-time recurrent…

Machine Learning · Computer Science 2024-10-31 Esraa Elelimy , Adam White , Michael Bowling , Martha White

Medical time-series data are characterized by irregular sampling, high noise levels, missing values, and strong inter-feature dependencies. Recurrent neural networks (RNNs), particularly gated architectures such as Long Short-Term Memory…

Machine Learning · Computer Science 2026-03-03 Maitri Krishna Sai

The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR). To estimate the output distributions over subword units, RNN-T uses a fully connected…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-26 Chao Zhang , Bo Li , Zhiyun Lu , Tara N. Sainath , Shuo-yiin Chang

This paper proposes a Fast Graph Convolutional Neural Network (FGRNN) architecture to predict sequences with an underlying graph structure. The proposed architecture addresses the limitations of the standard recurrent neural network (RNN),…

Signal Processing · Electrical Eng. & Systems 2020-01-28 Sai Kiran Kadambari , Sundeep Prabhakar Chepuri

Billions of text analysis requests containing private emails, personal text messages, and sensitive online reviews, are processed by recurrent neural networks (RNNs) deployed on public clouds every day. Although prior secure networks…

Cryptography and Security · Computer Science 2021-09-13 Bo Feng , Qian Lou , Lei Jiang , Geoffrey C. Fox

Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments. SE focuses on improving the auditory quality of speech, but the enhanced feature distribution is…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-04 Tianrui Wang , Weibin Zhu , Yingying Gao , Junlan Feng , Shilei Zhang

In this work, we investigate application of generative speech enhancement to improve the robustness of ASR models in noisy and reverberant conditions. We employ a recently-proposed speech enhancement model based on Schr\"odinger bridge,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-09 Rauf Nasretdinov , Roman Korostik , Ante Jukić

Epilepsy is common neurological diseases, affecting about 0.6-0.8 % of world population. Epileptic patients suffer from chronic unprovoked seizures, which can result in broad spectrum of debilitating medical and social consequences. Since…

Quantitative Methods · Quantitative Biology 2017-06-13 Sachin S. Talathi

Single-channel speech enhancement algorithms are often used in resource-constrained embedded devices, where low latency and low complexity designs gain more importance. In recent years, researchers have proposed a wide variety of novel…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-29 Nicolás Arrieta Larraza , Niels de Koeijer

In this paper, a neural network based real-time speech recognition (SR) system is developed using an FPGA for very low-power operation. The implemented system employs two recurrent neural networks (RNNs); one is a speech-to-character RNN…

Computation and Language · Computer Science 2016-10-04 Minjae Lee , Kyuyeon Hwang , Jinhwan Park , Sungwook Choi , Sungho Shin , Wonyong Sung

We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks. The architecture enables a dynamic pivot for its runtime…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-05 Jonathan Macoskey , Grant P. Strimel , Ariya Rastrow

While reasoning over long context is crucial for various real-world applications, it remains challenging for large language models (LLMs) as they suffer from performance degradation as the context length grows. Recent work MemAgent has…

Computation and Language · Computer Science 2026-02-12 Leheng Sheng , Yongtao Zhang , Wenchang Ma , Yaorui Shi , Ting Huang , Xiang Wang , An Zhang , Ke Shen , Tat-Seng Chua

In this paper, we present a novel approach to modeling long-term dependencies in sequential data by introducing a gated recurrent unit (GRU) with a weighted time-delay feedback mechanism. Our proposed model, named $\tau$-GRU, is a…

Machine Learning · Computer Science 2025-05-21 N. Benjamin Erichson , Soon Hoe Lim , Michael W. Mahoney

In this paper, we address three challenges in utterance-level emotion recognition in dialogue systems: (1) the same word can deliver different emotions in different contexts; (2) some emotions are rarely seen in general dialogues; (3)…

Computation and Language · Computer Science 2019-04-10 Wenxiang Jiao , Haiqin Yang , Irwin King , Michael R. Lyu

Recurrent neural networks have shown remarkable success in modeling sequences. However low resource situations still adversely affect the generalizability of these models. We introduce a new family of models, called Lattice Recurrent Units…

Machine Learning · Computer Science 2017-11-23 Chaitanya Ahuja , Louis-Philippe Morency

To improve the training efficiency of hierarchical recurrent models without compromising their performance, we propose a strategy named as `the lower the simpler', which is to simplify the baseline models by making the lower layers simpler…

Computation and Language · Computer Science 2019-05-22 Chao Wang , Hui Jiang

Plain recurrent networks greatly suffer from the vanishing gradient problem while Gated Neural Networks (GNNs) such as Long-short Term Memory (LSTM) and Gated Recurrent Unit (GRU) deliver promising results in many sequence learning tasks…

Neural and Evolutionary Computing · Computer Science 2019-07-08 Yuhuang Hu , Adrian Huber , Jithendar Anumula , Shih-Chii Liu

The use of future contextual information is typically shown to be helpful for acoustic modeling. Recently, we proposed a RNN model called minimal gated recurrent unit with input projection (mGRUIP), in which a context module namely temporal…

Computation and Language · Computer Science 2018-11-27 Jie Li , Yahui Shan , Xiaorui Wang , Yan Li

Noise robustness is critical when applying automatic speech recognition (ASR) in real-world scenarios. One solution involves the used of speech enhancement (SE) models as the front end of ASR. However, neural network-based (NN-based) SE…

Building systems that can communicate with humans is a core problem in Artificial Intelligence. This work proposes a novel neural network architecture for response selection in an end-to-end multi-turn conversational dialogue setting. The…

Artificial Intelligence · Computer Science 2018-11-06 Debanjan Chaudhuri , Agustinus Kristiadi , Jens Lehmann , Asja Fischer