Resource Type

Journal Article 54

Year

2023 10

2022 3

2021 4

2020 4

2019 1

2018 5

2017 2

2014 13

2010 1

2008 2

2007 2

2006 2

2005 1

2004 1

2002 1

2000 2

open ︾

Keywords

membrane separation 4

Gas separation 3

Membrane separation 2

Metal– 2

Metal–organic frameworks 2

Speech recognition 2

membrane technology 2

pervaporation 2

polyvinylidene fluoride 2

-/ 1

-butene 1

3D scaffold platform 1

5G 1

Haemophilus parasuis 1

Ochrobactrum anthropi 1

Adsorption and separation 1

Advanced manufacturing 1

Airflow acceleration classification 1

Analysis filter 1

open ︾

Search scope:

排序： Display mode:

Latent source-specific generative factor learning for monaural speech separation using weighted-factor autoencoder

Jing-jing Chen, Qi-rong Mao, You-cai Qin, Shuang-qing Qian, Zhi-shen Zheng,2221808071@stmail.ujs.edu.cn,mao_qr@ujs.edu.cn,2211908026@stmail.ujs.edu.cn,2211908025@stmail.ujs.edu.cn,3160602062@stmail.ujs.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 11,   Pages 1535-1670 doi: 10.1631/FITEE.2000019

Abstract: Much recent progress in monaural (MSS) has been achieved through a series of architectures based on s, which use an encoder to condense the input signal into compressed features and then feed these features into a decoder to construct a specific audio source of interest. However, these approaches can neither learn of the original input for MSS nor construct each audio source in mixed speech. In this study, we propose a novel weighted-factor (WFAE) model for MSS, which introduces a regularization loss in the objective function to isolate one source without containing other sources. By incorporating a latent attention mechanism and a supervised source constructor in the separation layer, WFAE can learn source-specific and a set of discriminative features for each source, leading to MSS performance improvement. Experiments on benchmark datasets show that our approach outperforms the existing methods. In terms of three important metrics, WFAE has great success on a relatively challenging MSS case, i.e., speaker-independent MSS.

Keywords： 语音分离；生成因子；自动编码器；深度学习    

HTML PDF Collect

A composite optimization method for separation parameters of large-eccentricity pico-satellites None

Lai TENG, Zhong-he JIN

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 5,   Pages 685-698 doi: 10.1631/FITEE.1700416

Abstract: A spacecraft’s separation parameters directly affect its flying trace. If the parameters exceed their limits, it will be difficult to adjust the flying attitude of the spacecraft, and the spacescraft may go off-track or crash. In this paper, we present a composite optimization method, which combines angular velocities with external moments for separation parameters of large-eccentricity pico-satellites. By changing the positions of elastic launch devices, the method effectively controls the popping process under the condition of less change in the separation mechanism. Finally, the reasons for deviation of angular velocities and unreliable optimization results are presented and analyzed. This optimization method is proved through a ground test which offsets the gravity. Simulation and test results show that the optimization method can effectively optimize the separation parameters of large-eccentricity pico-satellites. The proposed method adapts particularly to the fixed and non-stable status elastic parameters, the distribution of all kinds of elastic devices, and large-eccentricity spacecrafts for which attitude corrections are difficult. It is generally applicable and easy to operate in practical applications.

Keywords： Pico-satellite     Satellite–rocket separation mechanism     Separation parameters     Parameter optimization    

HTML PDF Collect

A subband excitation substitute based scheme for narrowband speech watermarking Article

Wei LIU, Ai-qun HU

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 5,   Pages 627-643 doi: 10.1631/FITEE.1601503

Abstract: We propose a new narrowband speech watermarking scheme by replacing part of the speech with a scaled and spectrally shaped hidden signal. Theoretically, it is proved that if a small amount of host speech is modified, then not only an ideal channel model for hidden communication can be established, but also high imperceptibility and good intelligibility can be achieved. Furthermore, a practical system implementation is proposed. At the embedder, the power normalization criterion is first imposed on a passband watermark signal by forcing its power level to be the same as the original passband excitation of the cover speech, and a synthesis filter is then used to spectrally shape the scaled watermark signal. At the extractor, a bandpass filter is first used to get rid of the out-of-band signal, and an analysis filter is then employed to compensate for the distortion introduced by the synthesis filter. Experimental results show that the data rate is as high as 400 bits/s with better bandwidth efficiency, and good imperceptibility is achieved. Moreover, this method is robust against various attacks existing in real applications.

Keywords： Analysis filter     Linear prediction     Narrowband speech watermarking     Passband excitation replacement     Power normalization     Spectral envelope shaping     Synthesis filter    

HTML PDF Collect

Multi-band Synchronization Model for Speech Recognition Under Noisy Condition

Sun Wei,Wu Zhenyang

Strategic Study of CAE 2006, Volume 8, Issue 3,   Pages 31-34

Abstract:

Based on perception characteristic of human ear, this paper proposes synchronization multi-band maximum likelihood linear regression algorithm for robust speech recognition under noisy condition. The algorithm utilizes maximum likelihood as estimation criteria to compensate the effects of noisy condition with multi-band synchronization model and noise corruption assumption. The tests show that the proposed algorithm improves the performance of recognition system effectively.

Keywords： hidden Markov model     maximum likelihood     multi-band synchronization model     speech recognition    

HTML PDF Collect

Capacity of VoIP in IEEE 802.11 Wireless LAN

Chen Liquan,Hu Aiqun,Zhou Xueli

Strategic Study of CAE 2005, Volume 7, Issue 7,   Pages 81-85

Abstract:

Voice transmitted over wireless LAN faces serious challenge because of the fluctuation of the wireless channel. In this paper, the transmission of voice over wireless LAN is firstly analyzed. Taking collision probability into account, the stochastic analysis based on a Markov chain to calculate the upper bound number of simultaneous VoIP calls that can be supported in a single cell of an IEEE 802. llb/a/g network is proposed. The upper bound capacities of G. 711, G. 729 and G. 723.1 code transmitted over 802. llb/a/g are figured out. The simulation results from NS2 simulator have validated the analysis values.

Keywords： wireless LAN     voice over IP     capacity     Markov chain    

HTML PDF Collect

Binary neural networks for speech recognition Regular Papers

Yan-min QIAN, Xu XIANG

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 5,   Pages 701-715 doi: 10.1631/FITEE.1800469

Abstract:

Recently, deep neural networks (DNNs) significantly outperform Gaussian mixture models in acoustic modeling for speech recognition. However, the substantial increase in computational load during the inference stage makes deep models difficult to directly deploy on low-power embedded devices. To alleviate this issue, structure sparseness and low precision fixed-point quantization have been applied widely. In this work, binary neural networks for speech recognition are developed to reduce the computational cost during the inference stage. A fast implementation of binary matrix multiplication is introduced. On modern central processing unit (CPU) and graphics processing unit (GPU) architectures, a 5–7 times speedup compared with full precision floatingpoint matrix multiplication can be achieved in real applications. Several kinds of binary neural networks and related model optimization algorithms are developed for large vocabulary continuous speech recognition acoustic modeling. In addition, to improve the accuracy of binary models, knowledge distillation from the normal full precision floating-point model to the compressed binary model is explored. Experiments on the standard Switchboard speech recognition task show that the proposed binary neural networks can deliver 3–4 times speedup over the normal full precision deep models. With the knowledge distillation from the normal floating-point models, the binary DNNs or binary convolutional neural networks (CNNs) can restrict the word error rate (WER) degradation to within 15.0%, compared to the normal full precision floating-point DNNs or CNNs, respectively. Particularly for the binary CNN with binarization only on the convolutional layers, the WER degradation is very small and is almost negligible with the proposed approach.

Keywords： Speech recognition     Binary neural networks     Binary matrix multiplication     Knowledge distillation     Population count    

HTML PDF Collect

Efficient decoding self-attention for end-to-end speech synthesis Research Article

Wei ZHAO, Li XU

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 7,   Pages 1127-1138 doi: 10.1631/FITEE.2100501

Abstract: has been innovatively applied to text-to-speech (TTS) because of its parallel structure and superior strength in modeling sequential data. However, when used in with an autoregressive decoding scheme, its inference speed becomes relatively low due to the quadratic complexity in sequence length. This problem becomes particularly severe on devices without graphics processing units (GPUs). To alleviate the dilemma, we propose an (EDSA) module as an alternative. Combined with a dynamic programming decoding procedure, TTS model inference can be effectively accelerated to have a linear computation complexity. We conduct studies on Mandarin and English datasets and find that our proposed model with EDSA can achieve 720% and 50% higher inference speed on the central processing unit (CPU) and GPU respectively, with almost the same performance. Thus, this method may make the deployment of such models easier when there are limited GPU resources. In addition, our model may perform better than the baseline Transformer TTS on out-of-domain utterances.

Keywords： Efficient decoding     End-to-end     Self-attention     Speech synthesis    

HTML PDF Collect

Study on Lighting Structure of Interactive Globe

Guo Yangkuan,Li Yinghui,Xu Wei,Xiong Qi,Ma Jing,Wang Yong,Song Yu

Strategic Study of CAE 2007, Volume 9, Issue 5,   Pages 50-52

Abstract:

Stated the principle of the talking globe, the lighting structure of the globe was studied,  and so were clear lighting for capitals,  diode's distribution,  and resolving power.  Then the talking globe was manufactured successfully. The method used in the article give a path for solving such problems.

Keywords： talking globe     structure design     resolving power     tube for bounding light     clear lighting    

HTML PDF Collect

One-Step Synthesis of Structurally Stable CO2-Philic Membranes with Ultra-High PEO Loading for Enhanced Carbon Capture Article

Bin Zhu, Shanshan He, Yadong Wu, Songwei Li, Lu Shao

Engineering 2023, Volume 26, Issue 7,   Pages 220-228 doi: 10.1016/j.eng.2022.03.016

Abstract:

Membrane technology has been considered a promising strategy for carbon capture to mitigate the effects of increasing atmospheric CO2 levels because CO2-philic membranes have demonstrated significant application potential, especially, for CO2/light gas separation. In this regard, poly(ethylene oxide) (PEO), which is a representative CO2-philic material, has attracted extensive research attention owing to its specific dipole–quadrupole interaction with CO2. Herein, we report a facile one-step synthesis protocol via the in situ polymerization of highly flexible polyethylene glycol to overcome the limitations of PEO, including high crystallinity and poor mechanical strength. The robust structure derived from intricate entanglements between short PEO chains and the polymer matrix enables an extremely high loading of linear polyethylene glycol (up to 90 wt%). Consequently, the separation performance easily surpasses the upper-bound limit. Moreover, the high structural stability allows for the concurrent increase of CO2 permeability and CO2/light gas selectivity at high feed pressure (up to 20 bar). This study provides a promising strategy to simultaneously improve the toughness and gas separation properties of all-polymeric membranes, demonstrating significant potential for industrial carbon capture and gas purification.

Keywords： Membrane separation     Gas separation     CO2 capture     CO2-philic membrane     Poly(ethylene oxide)    

HTML PDF Collect

The application of membrane separation technology in solving water security problem

Hou Li´an,Zhang Lin

Strategic Study of CAE 2014, Volume 16, Issue 7,   Pages 4-9

Abstract:

During the past 20 years, membrane technology industry has achieved great development both in China and abroad, meanwhile, membrane technology plays an important role in solving water security problem. In this article, the development of membrane separation technology and its applications in deep treatment of drinking water, wastewater treatment, emergency water supplies and special wastewater treatment were summarized.

Keywords： water security     membrane separation     ultrafiltration     nanofiltration     reverse osmosis    

HTML PDF Collect

A Smart Metasurface for Electromagnetic Manipulation Based on Speech Recognition Article

Lin Bai, Yuan Ke Liu, Liang Xu, Zheng Zhang, Qiang Wang, Wei Xiang Jiang, Cheng-Wei Qiu, Tie Jun Cui

Engineering 2023, Volume 22, Issue 3,   Pages 185-190 doi: 10.1016/j.eng.2022.06.026

Abstract:

In this work, we propose and realize a smart metasurface for programming electromagnetic (EM) manipulations based on human speech recognition. The smart metasurface platform is composed of a digital coding metasurface, a speech-recognition module, a single-chip computer, and a digital-to-analog converter (DAC) circuit, and can control EM waves according to pre-stored voice commands in a smart way. The constructed digital metasurface contains 6 × 6 super unit cells, each of which consists of 4 × 4 active elements with embedded varactor diodes. Together with the DAC and single-chip computer, the speech-recognition module can recognize voice commands and generate corresponding voltage sequences to control the metasurface. In addition, a genetic algorithm (GA) is adopted in the design of the metasurface for efficiently optimizing the phase distributions. To verify the performance of the smart metasurface platform, three typical functions are demonstrated: radar cross-section reduction, vortex beam generation, and beam splitting. The proposed strategy may offer a new avenue for controlling EM waves and establishing a link between EM and acoustic communications.

Keywords： Speech recognition     Programmable metasurface     Genetic algorithm     Smart electromagnetic manipulation    

HTML PDF Collect

Numerical analysis on different lateral inlet cyclone flow field

Chen Qidong and Zuo Zhiquan

Strategic Study of CAE 2014, Volume 16, Issue 2,   Pages 58-67

Abstract:

Numerical simulation and calculation were performed on the gas-phase flow field of the straight tangential cyclone with single entry，straight tangential cyclone with double entries， bias tangential cyclone with single entry，bias tangential cyclone with double entries，bias tangential helicoidal cyclone with single entry，bias tangential helicoidal cyclone with double entries by using RSM model. Results showed that，the pressure field and velocity field of the cyclone with double entries had better symmetry and stability；only changing the inlet angle had a limited influence on the pressure field and velocity field. When the tangential velocity distribution were similar in the six kinds of cyclone studied in this article，compared with other cyclones’， the pressure drop of the bias tangential helicoidal cyclone decreased about 25 %；the inlet total pressure needed was about 17 % lower；the energy consumption dropped about 17 %. Moreover，bias tangential helicoidal cyclone with double entries（XS-L type）had a better energy efficiency ratio，and its performance was the most excellent.

Keywords： cyclone     lateral inlet     pressure drop     inlet total pressure     energy consumption    

HTML PDF Collect

Research and application on separation technology of slurry and water under sandy-gravel stratum

Wang Guangyu,Sun Shanhui,Su Qinggui

Strategic Study of CAE 2010, Volume 12, Issue 12,   Pages 41-45

Abstract:

This paper gives a summary on application technology of slurry and water separation in condition of sandy-gravels layers in city's busiest street on base of underground diameter project from Beijing railway station to Beijing railway west station,with the hope of providing reference to the future similar project.

Keywords： slurry tunnel machine     separation of slurry and water     filter-press    

HTML PDF Collect

Gathers flows the separation formula irrigation pattern research and the practice

Zhang Jianghui,Zhou Heping,Xu Xiaobo,Yao Xinhua

Strategic Study of CAE 2008, Volume 10, Issue 9,   Pages 25-30

Abstract:

Gathers flows the separation formula irrigation is a new water-saving irrigation pattern, which is based on the characteristic and request that thinly plants the fruit-growing class industrial crop needs water and is proposed on the basis of innovation technical experiment and practice in recent years. This paper summarized the basic idea of gathers flows the separation formula irrigation pattern, elaborated the key technologies of gathers flows the irrigation system, and that is gathers flows the separation formula douche, analyzed the comprehensive technical effect of gathers flows the separation formula irrigation pattern, including saving water to increase production, conserving energy and consumption, raising irrigation water temperature and solving the problem of irrigation unlevelness in low head conditions and pointed out the main problems which should be focused in future.

Keywords： water-saving agriculture     gathers flows the separation irrigation pattern     innovation research     practice    

HTML PDF Collect

Advancements in MOF-Based Engineered Materials for Efficient Separation Processes

Qilong Ren

Engineering 2023, Volume 23, Issue 4,   Pages 1-2 doi: 10.1016/j.eng.2023.02.006

HTML PDF Collect

Title Author Date Type Operation

Latent source-specific generative factor learning for monaural speech separation using weighted-factor autoencoder

Jing-jing Chen, Qi-rong Mao, You-cai Qin, Shuang-qing Qian, Zhi-shen Zheng,2221808071@stmail.ujs.edu.cn,mao_qr@ujs.edu.cn,2211908026@stmail.ujs.edu.cn,2211908025@stmail.ujs.edu.cn,3160602062@stmail.ujs.edu.cn

Journal Article

A composite optimization method for separation parameters of large-eccentricity pico-satellites

Lai TENG, Zhong-he JIN

Journal Article

A subband excitation substitute based scheme for narrowband speech watermarking

Wei LIU, Ai-qun HU

Journal Article

Multi-band Synchronization Model for Speech Recognition Under Noisy Condition

Sun Wei,Wu Zhenyang

Journal Article

Capacity of VoIP in IEEE 802.11 Wireless LAN

Chen Liquan,Hu Aiqun,Zhou Xueli

Journal Article

Binary neural networks for speech recognition

Yan-min QIAN, Xu XIANG

Journal Article

Efficient decoding self-attention for end-to-end speech synthesis

Wei ZHAO, Li XU

Journal Article

Study on Lighting Structure of Interactive Globe

Guo Yangkuan,Li Yinghui,Xu Wei,Xiong Qi,Ma Jing,Wang Yong,Song Yu

Journal Article

One-Step Synthesis of Structurally Stable CO2-Philic Membranes with Ultra-High PEO Loading for Enhanced Carbon Capture

Bin Zhu, Shanshan He, Yadong Wu, Songwei Li, Lu Shao

Journal Article

The application of membrane separation technology in solving water security problem

Hou Li´an,Zhang Lin

Journal Article

A Smart Metasurface for Electromagnetic Manipulation Based on Speech Recognition

Lin Bai, Yuan Ke Liu, Liang Xu, Zheng Zhang, Qiang Wang, Wei Xiang Jiang, Cheng-Wei Qiu, Tie Jun Cui

Journal Article

Numerical analysis on different lateral inlet cyclone flow field

Chen Qidong and Zuo Zhiquan

Journal Article

Research and application on separation technology of slurry and water under sandy-gravel stratum

Wang Guangyu,Sun Shanhui,Su Qinggui

Journal Article

Gathers flows the separation formula irrigation pattern research and the practice

Zhang Jianghui,Zhou Heping,Xu Xiaobo,Yao Xinhua

Journal Article

Advancements in MOF-Based Engineered Materials for Efficient Separation Processes

Qilong Ren

Journal Article