中文
相关论文

相关论文: Small-footprint Deep Neural Networks with Highway …

200 篇论文

State-of-the-art speech recognition systems typically employ neural network acoustic models. However, compared to Gaussian mixture models, deep neural network (DNN) based acoustic models often have many more model parameters, making it…

计算与语言 · 计算机科学 2017-04-27 Liang Lu , Steve Renals

Deep learning has significantly advanced state-of-the-art of speech recognition in the past few years. However, compared to conventional Gaussian mixture acoustic models, neural network models are usually much larger, and are therefore not…

计算与语言 · 计算机科学 2016-12-22 Liang Lu , Michelle Guo , Steve Renals

Highway deep neural network (HDNN) is a type of depth-gated feedforward neural network, which has shown to be easier to train with more hidden layers and also generalise better compared to conventional plain deep neural networks (DNNs).…

计算与语言 · 计算机科学 2017-03-23 Liang Lu

Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved…

机器学习 · 计算机科学 2018-12-06 Dong Yu , Michael L. Seltzer , Jinyu Li , Jui-Ting Huang , Frank Seide

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…

计算与语言 · 计算机科学 2016-08-18 Jeehye Lee , Myungin Lee , Joon-Hyuk Chang

Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Building neural network acoustic models requires several design decisions including network architecture, size, and training…

计算与语言 · 计算机科学 2015-01-21 Andrew L. Maas , Peng Qi , Ziang Xie , Awni Y. Hannun , Christopher T. Lengerich , Daniel Jurafsky , Andrew Y. Ng

Despite showing state-of-the-art performance, deep learning for speech recognition remains challenging to deploy in on-device edge scenarios such as mobile and other consumer devices. Recently, there have been greater efforts in the design…

音频与语音处理 · 电气工程与系统科学 2018-11-15 Zhong Qiu Lin , Audrey G. Chung , Alexander Wong

In this paper, various structures and methods of Deep Artificial Neural Networks (DNN) will be evaluated and compared for the purpose of continuous Persian speech recognition. One of the first models of neural networks used in speech…

音频与语音处理 · 电气工程与系统科学 2021-05-06 Arash Dehghani , Seyyed Ali Seyyedsalehi

In this paper, we extend the deep long short-term memory (DLSTM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers. These direct links, called highway connections, enable unimpeded…

神经与进化计算 · 计算机科学 2018-12-06 Yu Zhang , Guoguo Chen , Dong Yu , Kaisheng Yao , Sanjeev Khudanpur , James Glass

We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of low-dimensional subspaces. To that end, the training posteriors are used for dictionary learning and sparse coding.…

计算与语言 · 计算机科学 2017-09-07 Pranay Dighe , Gil Luyet , Afsaneh Asaei , Herve Bourlard

Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult…

音频与语音处理 · 电气工程与系统科学 2020-03-10 Vincent Roger , Jérôme Farinas , Julien Pinquier

Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the targets for DNN training. Subword classes in speech recognition…

计算与语言 · 计算机科学 2017-09-07 Pranay Dighe , Afsaneh Asaei , Herve Bourlard

In this work, we propose small footprint Convolutional Recurrent Neural Network models applied to the problem of wakeword detection and augment them with scaled dot product attention. We find that false accepts compared to Convolutional…

音频与语音处理 · 电气工程与系统科学 2020-11-26 Mohammad Omar Khursheed , Christin Jose , Rajath Kumar , Gengshen Fu , Brian Kulis , Santosh Kumar Cheekatmalla

This paper presents a novel machine-hearing system that exploits deep neural networks (DNNs) and head movements for robust binaural localisation of multiple sources in reverberant environments. DNNs are used to learn the relationship…

音频与语音处理 · 电气工程与系统科学 2019-04-08 Ning Ma , Tobias May , Guy J. Brown

This paper presents our latest investigation on Densely Connected Convolutional Networks (DenseNets) for acoustic modelling (AM) in automatic speech recognition. DenseN-ets are very deep, compact convolutional neural networks, which have…

计算与语言 · 计算机科学 2018-08-13 Chia Yu Li , Ngoc Thang Vu

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…

计算与语言 · 计算机科学 2015-07-27 Haşim Sak , Andrew Senior , Kanishka Rao , Françoise Beaufays

Observational studies are based on accurate assessment of human state. A behavior recognition system that models interlocutors' state in real-time can significantly aid the mental health domain. However, behavior recognition from speech…

机器学习 · 计算机科学 2016-06-15 Haoqi Li , Brian Baucom , Panayiotis Georgiou

Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech…

机器学习 · 计算机科学 2016-06-16 Zhenzhou Wu , Sunil Sivadas , Yong Kiam Tan , Ma Bin , Rick Siow Mong Goh

In modern transportation systems, an enormous amount of traffic data is generated every day. This has led to rapid progress in short-term traffic prediction (STTP), in which deep learning methods have recently been applied. In traffic…

机器学习 · 计算机科学 2020-09-03 Kyungeun Lee , Moonjung Eo , Euna Jung , Yoonjin Yoon , Wonjong Rhee

Artificial neural networks (ANN) have become the mainstream acoustic modeling technique for large vocabulary automatic speech recognition (ASR). A conventional ANN features a multi-layer architecture that requires massive amounts of…

神经与进化计算 · 计算机科学 2019-11-20 Jibin Wu , Emre Yilmaz , Malu Zhang , Haizhou Li , Kay Chen Tan
‹ 上一页 1 2 3 10 下一页 ›