AI2.0时代的类人与超人感知：研究综述与趋势展望

田永鸿; 陈熙霖; 熊红凯; 李洪亮; 戴礼荣; 陈婧; 兴军亮; 陈靖; 吴玺宏; 胡卫明; 胡郁; 黄铁军; 高文

doi:10.1631/FITEE.1601804

Your Location：

Home >

Browse articles >

AI2.0时代的类人与超人感知：研究综述与趋势展望

人工智能2.0专辑 | Updated：2022-05-19

- AI2.0时代的类人与超人感知：研究综述与趋势展望
- Towards human-like and transhuman perception in AI 2.0: a review
- 信息与电子工程前沿（英文） 2017年18卷第1期页码：58-67
- Affiliations：
  
  1School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China
  2Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
  3Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
  4School of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu 611730, China
  5Department of Electronic Engineering and Information Sciences, University of Science and Technology of China, Hefei 230027, China
  6Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
  7School of Optoelectronics, Beijing Institute of Technology, Beijing 100081, China
- Author bio：
  
  E-mail:yhtian@pku.edu.cn
  E-mail:tjhuang@pku.edu.cn
- Funds：
  
  Project supported by the Strategic Consulting Research Project of Chinese Academy of Engineering (No. 2016-ZD-04-03)
- DOI：10.1631/FITEE.1601804
  中图分类号： TP391
- 收稿：2016-12-12，
  
  录用：2016-12-26，
  
  纸质出版：2017-01
- Accepted：
Scan QR Code
田永鸿, 陈熙霖, 熊红凯, 等. AI2.0时代的类人与超人感知：研究综述与趋势展望[J]. 信息与电子工程前沿（英文）, 2017,18(1):58-67.

Yong-hong TIAN, Xi-lin CHEN, Hong-kai XIONG, et al. Towards human-like and transhuman perception in AI 2.0: a review[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(1): 58-67.
田永鸿, 陈熙霖, 熊红凯, 等. AI2.0时代的类人与超人感知：研究综述与趋势展望[J]. 信息与电子工程前沿（英文）, 2017,18(1):58-67. DOI： 10.1631/FITEE.1601804.

Yong-hong TIAN, Xi-lin CHEN, Hong-kai XIONG, et al. Towards human-like and transhuman perception in AI 2.0: a review[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(1): 58-67. DOI： 10.1631/FITEE.1601804.

摘要

感知是智能系统与现实世界的交互界面。如果没有复杂而灵活的感知能力，就不可能创造出高级的人工智能（Artificial intelligence

AI）系统。最近，潘云鹤院士提出了AI2.0的概念，其最重要的特征就是未来的AI系统应拥有类人甚至超人的智能感知能力。本文简要回顾了不同智能感知领域的研究现状，包括视觉感知、听觉感知、言语感知、感知信息处理与学习引擎等方面。在此基础上，论文对即将到来的AI 2.0时代智能感知领域需要大力研究发展的重点方向进行了展望，包括：（1）类人和超人的主动视觉；（2）自然声学场景的听知觉感知；（3）自然交互环境的言语感知及计算；（4）面向媒体感知的自主学习；（5）大规模感知信息处理与学习引擎；（6）城市全维度智能感知推理引擎。这些研究方向应在未来AI2.0的研究规划中进行重点布局。

Abstract

Perception is the interaction interface between an intelligent system and the real world. Without sophisticated and flexible perceptual capabilities

it is impossible to create advanced artificial intelligence (AI) systems. For the next-generation AI

called 'AI 2.0'

one of the most significant features will be that AI is empowered with intelligent perceptual capabilities

which can simulate human brain's mechanisms and are likely to surpass human brain in terms of performance. In this paper

we briefly review the state-of-the-art advances across different areas of perception

including visual perception

auditory perception

speech perception

and perceptual information processing and learning engines. On this basis

we envision several R & D trends in intelligent perception for the forthcoming era of AI 2.0

including: (1) human-like and transhuman active vision; (2) auditory perception and computation in an actual auditory setting; (3) speech perception and computation in a natural interaction setting; (4) autonomous learning of perceptual information; (5) large-scale perceptual information processing and learning platforms; and (6) urban omnidirectional intelligent perception and reasoning engines. We believe these research directions should be highlighted in the future plans for AI 2.0.

关键词

Keywords

references

D Amodei , , , R Anubhai , , , E Battenberg , , , 等 . . Deep Speech 2: end-to-end speech recognition in English and Mandarin . . 2015 . . arXiv:1512.02595 . . . .

MF Bear , , , BW Connors , , , MA Paradiso . . Neuroscience . . 2001 . . Lippincott Williams and Wilkins, Maryland . . 208 . .

J Bruna , , , S Mallat . . Invariant scattering convolution networks . . IEEE Trans. Patt. Anal. Mach. Intell. , , 2013 . . 35 ( ( 8 ): ): 1872 - - 1886 . . DOI: 10.1109/TPAMI.2012.230 http://doi.org/10.1109/TPAMI.2012.230 . .

E Cand s , , , J Romberg , , , T Tao . . Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information . . IEEE Trans. Inform. Theory , , 2006 . . 52 ( ( 2 ): ): 489 - - 509 . . DOI: 10.1109/TIT.2005.862083 http://doi.org/10.1109/TIT.2005.862083 . .

J Deng , , , W Dong , , , R Socher , , , 等 . . ImageNet: a large-scale hierarchical image database . . 2009 . . IEEE Conf. on Computer Vision and Pattern Recognition . . 248 - - 255 . . DOI: 10.1109/CVPR.2009.5206848 http://doi.org/10.1109/CVPR.2009.5206848 . .

M Duarte , , , M Davenport , , , D Takhar , , , 等 . . Single-pixel imaging via compressive sampling . . IEEE Signal Proc. Mag. , , 2008 . . 25 ( ( 2 ): ): 83 - - 91 . . DOI: 10.1109/MSP.2007.914730 http://doi.org/10.1109/MSP.2007.914730 . .

J Han , , , L Shao , , , D Xu , , , 等 . . Enhanced computer vision with Microsoft Kinect sensor: a review . . IEEE Trans. Cybern. , , 2013 . . 43 ( ( 5 ): ): 1318 - - 1334 . . DOI: 10.1109/TCYB.2013.2265378 http://doi.org/10.1109/TCYB.2013.2265378 . .

G Hinton , , , L Deng , , , D Yu , , , 等 . . Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups . . IEEE Signal Proc. Mag. , , 2012 . . 29 ( ( 6 ): ): 82 - - 97 . . DOI: 10.1109/MSP.2012.2205597 http://doi.org/10.1109/MSP.2012.2205597 . .

S Hochreiter , , , J Schmidhuber . . Long short-term memory . . Neur. Comput. , , 1997 . . 9 ( ( 8 ): ): 1735 - - 1780 . . DOI: 10.1162/neco.1997.9.8.1735 http://doi.org/10.1162/neco.1997.9.8.1735 . .

YZ Hou , , , LF Jiao . . Survey of smart city construction study from home and abroad . . Ind. Sci. Trib. , , 2014 . . 13 ( ( 24 ): ): 94 - - 97 . . . .

H Jiang , , , G Huang , , , P Wilford . . Multi-view in lensless compressive imaging . . Apsipa Trans. Signal Inform. Proc. , , 2014 . . 3 ( ( 15 ): ): 1 - - 10 . . DOI: 10.1109/PCS.2013.6737678 http://doi.org/10.1109/PCS.2013.6737678 . .

A Kadambi , , , R Whyte , , , A Bhandari , , , 等 . . Coded time of flight cameras: sparse deconvolution to address multipath interference and recover time profiles . . ACM Trans. Graph. , , 2013 . . 32 ( ( 6 ): ): 1 - - 10 . . DOI: 10.1145/2508363.2508428 http://doi.org/10.1145/2508363.2508428 . .

PV Kale , , , SD Sharma . . A review of securing home using video surveillance . . Int. J. Sci. Res. , , 2014 . . 3 ( ( 5 ): ): 1150 - - 1154 . . . .

KM Kendrick . . Intelligent perception . . Appl. Animal Behav. Sci. , , 1998 . . 57 ( ( 3-4 ): ): 213 - - 231 . . DOI: 10.1016/S0168-1591(98)00098-7 http://doi.org/10.1016/S0168-1591(98)00098-7 . .

S King . . Measuring a decade of progress in text-to-speech . . Loquens , , 2014 . . 1 ( ( 1 ): ): e006 DOI: 10.3989/loquens.2014.006 http://doi.org/10.3989/loquens.2014.006 . .

A Krizhevsk , , , I Sutskever , , , G Hinton . . ImageNet classification with deep convolutional neural networks . . 2012 . . Advances in Neural Information Processing Systems . . 1097 - - 1105 . . . .

G Lacey , , , GW Taylor , , , S Areibi . . Deep learning on FPGAs: past, present, and future . . 2016 . . arXiv:1602.04283 . . . .

Y LeCun , , , Y Bengio , , , G Hinton . . Deep learning . . Nature , , 2015 . . 521 ( ( 7553 ): ): 436 - - 444 . . DOI: 10.1038/nature14539 http://doi.org/10.1038/nature14539 . .

T Li , , , H Chang , , , M Wang , , , 等 . . Crowded scene analysis: a survey . . IEEE Trans. Circ. Syst. Video Technol. , , 2015 . . 25 ( ( 3 ): ): 367 - - 386 . . DOI: 10.1109/TCSVT.2014.2358029 http://doi.org/10.1109/TCSVT.2014.2358029 . .

ZH Ling , , , SY Kang , , , H Zen , , , 等 . . Deep learning for acoustic modeling in parametric speech generation: a systematic review of existing techniques and future trends . . IEEE Signal Proc. Mag. , , 2015 . . 32 ( ( 3 ): ): 35 - - 52 . . DOI: 10.1109/MSP.2014.2359987 http://doi.org/10.1109/MSP.2014.2359987 . .

RP Lippmann . . Speech recognition by machines and humans . . Speech Commun. , , 1997 . . 22 ( ( 1 ): ): 1 - - 15 . . DOI: 10.1016/S0167-6393(97)00021-6 http://doi.org/10.1016/S0167-6393(97)00021-6 . .

RY Litovsky , , , HS Colburn , , , WA Yost , , , 等 . . The precedence effect . . J. Acoust. Soc. Am. , , 1999 . . 106 1633 - - 1654 . . DOI: 10.1121/1.427914 http://doi.org/10.1121/1.427914 . .

A Mahendran , , , A Vedaldi . . Understanding deep image representations by inverting them . . 2015 . . IEEE Int. Conf. on Computer Vision Pattern Recognition . . 5188 - - 5196 . . DOI: 10.1109/CVPR.2015.7299155 http://doi.org/10.1109/CVPR.2015.7299155 . .

J Makhoul . . A 50-year retrospective on speech and language processing . . 2016 . . Int. Conf. on Interspeech . . 1 . .

SL Mattys , , , MH Davis , , , AR Bradlow , , , 等 . . Speech recognition in adverse conditions: a review . . Lang. Cogn. Proc. , , 2012 . . 27 953 - - 978 . . DOI: 10.1080/01690965.2012.705006 http://doi.org/10.1080/01690965.2012.705006 . .

L McMackin , , , MA Herman , , , B Chatterjee , , , 等 . . A high-resolution SWIR camera via compressed sensing . . SPIE. , , 2012 . . 8353 835303 DOI: 10.1117/12.920050 http://doi.org/10.1117/12.920050 . .

V Mountcastle . . An organizing principle for cerebral function: the unit model and the distributed system. In: Edelman GM, Mountcastle, V.B. (Eds.), The Mindful Brain , , 1978 . . : Cambridge : MIT Press , , . .

P Musialski , , , P Wonka , , , DG Aliaga , , , 等 . . A survey of urban reconstruction . . Comput. Graph. Forum , , 2013 . . 32 ( ( 6 ): ): 146 - - 177 . . DOI: 10.1111/cgf.12077 http://doi.org/10.1111/cgf.12077 . .

J Ngiam , , , A Khosla , , , M Kim , , , 等 . . Multimodal deep learning . . 2011 . . 28th In. Conf. on Machine Learning . . 689 - - 696 . . . .

K Niwa , , , Y Koizumi , , , T Kawase , , , 等 . . Pinpoint extraction of distant sound source based on DNN mapping from multiple beamforming outputs to prior SNR . . 2016 . . IEEE Int. Conf. on Acoustics, Speech and Signal Processing . . 435 - - 439 . . . .

A Oord , , , S Dieleman , , , H Zen , , , 等 . . WaveNet: a generative model for raw audio . . 2016 . . arXiv:1609.03499 . . . .

YH Pan . . Heading toward artificial intelligence 2.0 . . Engineering , , 2016 . . 2 ( ( 4 ): ): 409 - - 413 . . DOI: 10.1016/J.ENG.2016.04.018 http://doi.org/10.1016/J.ENG.2016.04.018 . .

G Pratt , , , J Manzo . . The DARPA robotics challenge . . IEEE Robot. Autom. Mag. , , 2013 . . 20 ( ( 2 ): ): 10 - - 12 . . DOI: 10.1109/MRA.2013.2255424 http://doi.org/10.1109/MRA.2013.2255424 . .

FH Priano , , , RL Armas , , , CF Guerra . . A model for the smart development of island territories . . 2016 . . Int. Conf. on Digital Government Research . . 465 - - 474 . . DOI: 10.1145/2912160.2912187 http://doi.org/10.1145/2912160.2912187 . .

R Raina , , , A Battle , , , H Lee , , , 等 . . Self-taught learning: transfer learning from unlabeled data . . 2007 . . 24th Int. Conf. on Machine Learning . . 759 - - 766 . . DOI: 10.1145/1273496.1273592 http://doi.org/10.1145/1273496.1273592 . .

EA Robinson , , , S Treitel . . Principles of digital Wiener filtering . . Geophys. Prospect. , , 1967 . . 15 ( ( 3 ): ): 311 - - 332 . . DOI: 10.1111/j.1365-2478.1967.tb01793.x http://doi.org/10.1111/j.1365-2478.1967.tb01793.x . .

R Roy , , , T Kailath . . ESPRIT-estimation of signal parameters via rotational invariance techniques . . IEEE Trans. Acoust. Speech Signal Process. , , 1989 . . 37 ( ( 7 ): ): 984 - - 995 . . DOI: 10.1109/29.32276 http://doi.org/10.1109/29.32276 . .

R Salakhutdinov , , , G Hinton . . Deep Boltzmann machines . . J. Mach. Learn. Res. , , 2009 . . 5 448 - - 455 . . . .

G Saon , , , HKJ Kuo , , , S Rennie , , , 等 . . The IBM 2015 English conversational telephone speech recognition system . . 2015 . . arXiv:1505.05899 . . . .

F Seide , , , G Li , , , D Yu . . Conversational speech transcription using context-dependent deep neural networks . . 2011 . . Int. Conf. on Interspeech . . 437 - - 440 . . . .

H Soltau , , , G Saon , , , TN Sainath . . Joint training of convolutional and nonconvolutional neural networks . . 2014 . . IEEE Int. Conf. on Acoustics, Speech and Signal Processing . . 5572 - - 5576 . . DOI: 10.1109/ICASSP.2014.6854669 http://doi.org/10.1109/ICASSP.2014.6854669 . .

T Song , , , J Chen , , , DB Zhang , , , 等 . . A sound source localization algorithm using microphone array with rigid body . . 2016 . . Int. Congress on Acoustics . . 1 - - 8 . . . .

LR Suzuki . . Data as Infrastructure for Smart Cities , , 2015 . . : London, UK : University College London , , PhD Thesis . .

R Tadano , , , A Pediredla , , , A Veeraraghavan . . Depth selective camera: a direct, on-chip, programmable technique for depth selectivity in photography . . 2015 . . Int. Conf. on Computer Vision . . 3595 - - 3603 . . DOI: 10.1109/ICCV.2015.410 http://doi.org/10.1109/ICCV.2015.410 . .

K Tokuda , , , Y Nankaku , , , T Toda , , , 等 . . Speech synthesis based on hidden Markov models . . Proc. IEEE , , 2013 . . 101 ( ( 5 ): ): 1234 - - 1252 . . DOI: 10.1109/JPROC.2013.2251852 http://doi.org/10.1109/JPROC.2013.2251852 . .

M Turk , , , A Pentland . . Eigenfaces for recognition . . J. Cogn. Neurosci. , , 1991 . . 3 ( ( 1 ): ): 71 - - 86 . . DOI: 10.1162/jocn.1991.3.1.71 http://doi.org/10.1162/jocn.1991.3.1.71 . .

K Vesel , , , A Ghoshal , , , L Burget , , , 等 . . Sequence-discriminative training of deep neural networks . . 2013 . . Int. Conf. on Interspeech . . 2345 - - 2349 . . . .

W Wang , , , S Xu , , , B Xu . . First step towards end-to-end parametric TTS synthesis: generating spectral parameters with neural attention . . 2016 . . Int. Conf. on Interspeech . . 2243 - - 2247 . . DOI: 10.21437/Interspeech.2016-134 http://doi.org/10.21437/Interspeech.2016-134 . .

W Xiong , , , J Droppo , , , X Huang , , , 等 . . Achieving human parity in conversational speech recognition . . 2016 . . arXiv:1610.05256 . . . .

JP Zhang , , , FY Wang , , , KF Wang , , , 等 . . Data-driven intelligent transportation systems: a survey . . IEEE Trans. Intell. Transp. Syst. , , 2011 . . 12 ( ( 4 ): ): 1624 - - 1639 . . DOI: 10.1109/TITS.2011.2158001 http://doi.org/10.1109/TITS.2011.2158001 . .

L Zheng , , , Y Yang , , , AG Hauptmann . . Person re-identification: past, present and future . . 2016 . . arXiv:1610. 02984 . . . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据