English
Related papers

Related papers: Quaternion Convolutional Neural Networks for End-t…

200 papers

Neural network architectures are at the core of powerful automatic speech recognition systems (ASR). However, while recent researches focus on novel model architectures, the acoustic input features remain almost unchanged. Traditional ASR…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-27 Titouan Parcollet , Mirco Ravanelli , Mohamed Morchid , Georges Linarès , Renato De Mori

Recurrent neural networks (RNNs) are powerful architectures to model sequential data, due to their capability to learn short and long-term dependencies between the basic elements of a sequence. Nonetheless, popular tasks such as speech or…

Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition (ASR). Hybrid speech recognition systems incorporating CNNs…

Computation and Language · Computer Science 2017-01-11 Ying Zhang , Mohammad Pezeshki , Philemon Brakel , Saizheng Zhang , Cesar Laurent Yoshua Bengio , Aaron Courville

Connectionist temporal classification (CTC) is a popular sequence prediction approach for automatic speech recognition that is typically used with models based on recurrent neural networks (RNNs). We explore whether deep convolutional…

Computation and Language · Computer Science 2018-02-16 Kalpesh Krishna , Liang Lu , Kevin Gimpel , Karen Livescu

Since their first applications, Convolutional Neural Networks (CNNs) have solved problems that have advanced the state-of-the-art in several domains. CNNs represent information using real numbers. Despite encouraging results, theoretical…

Artificial Intelligence · Computer Science 2025-12-22 Gerardo Altamirano-Gomez , Carlos Gershenson

Conventional Convolutional Neural Networks (CNNs) in the real domain have been widely used for audio classification. However, their convolution operations process multi-channel inputs independently, limiting the ability to capture…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-27 Arshdeep Singh , Vinayak Abrol , Mark D. Plumbley

Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years. However, the extensions of the neural network models in other number fields and their potential…

Computer Vision and Pattern Recognition · Computer Science 2019-03-05 Xuanyu Zhu , Yi Xu , Hongteng Xu , Changjian Chen

Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we introduce the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly,…

Neural and Evolutionary Computing · Computer Science 2020-02-04 Marcos Eduardo Valle , Rodolfo Anibal Lobo

Deep learning approaches have been widely used in Automatic Speech Recognition (ASR) and they have achieved a significant accuracy improvement. Especially, Convolutional Neural Networks (CNNs) have been revisited in ASR recently. However,…

Computation and Language · Computer Science 2017-02-28 Yisen Wang , Xuejiao Deng , Songbai Pu , Zhiheng Huang

Deep neural networks (DNNs) and more precisely recurrent neural networks (RNNs) are at the core of modern automatic speech recognition systems, due to their efficiency to process input sequences. Recently, it has been shown that different…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-20 Titouan Parcollet , Mohamed Morchid , Georges Linarès , Renato De Mori

Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly,…

Machine Learning · Computer Science 2020-09-14 Marcos Eduardo Valle , Rodolfo Anibal Lobo

Recurrent neural networks (RNN) are at the core of modern automatic speech recognition (ASR) systems. In particular, long-short term memory (LSTM) recurrent neural networks have achieved state-of-the-art results in many speech recognition…

Audio and Speech Processing · Electrical Eng. & Systems 2018-11-08 Titouan Parcollet , Mohamed Morchid , Georges Linarès , Renato De Mori

Convolutional neural networks (CNN) have recently achieved state-of-the-art results in various applications. In the case of image recognition, an ideal model has to learn independently of the training data, both local dependencies between…

Computer Vision and Pattern Recognition · Computer Science 2018-11-08 Titouan Parcollet , Mohamed Morchid , Georges Linarès

We introduce a class of convolutional neural networks (CNNs) that utilize recurrent neural networks (RNNs) as convolution filters. A convolution filter is typically implemented as a linear affine transformation followed by a non-linear…

Computation and Language · Computer Science 2018-08-29 Yi Yang

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-24 Yanxin Hu , Yun Liu , Shubo Lv , Mengtao Xing , Shimin Zhang , Yihui Fu , Jian Wu , Bihong Zhang , Lei Xie

Despite the significant progress in automatic speech recognition (ASR), distant ASR remains challenging due to noise and reverberation. A common approach to mitigate this issue consists of equipping the recording devices with multiple…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-20 Xinchi Qiu , Titouan Parcollet , Mirco Ravanelli , Nicholas Lane , Mohamed Morchid

Tensor completion has emerged as a powerful framework for recovering missing data in multidimensional signals by exploiting low-rank tensor structures. Among existing approaches, linear transform-based tensor nuclear norm (TNN) methods have…

Optimization and Control · Mathematics 2026-05-05 Biswarup Karmakar , Ratikanta Behera

Connectionist temporal classification (CTC) based supervised sequence training of recurrent neural networks (RNNs) has shown great success in many machine learning areas including end-to-end speech and handwritten character recognition. For…

Machine Learning · Computer Science 2017-02-03 Kyuyeon Hwang , Wonyong Sung

Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are able to extract higher level features that are invariant to…

Machine Learning · Computer Science 2017-05-31 Emre Çakır , Giambattista Parascandolo , Toni Heittola , Heikki Huttunen , Tuomas Virtanen

The field of neural networks has seen significant advances in recent years with the development of deep and convolutional neural networks. Although many of the current works address real-valued models, recent studies reveal that neural…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Marco Aurélio Granero , Cristhian Xavier Hernández , Marcos Eduardo Valle
‹ Prev 1 2 3 10 Next ›