Exploring the Relative Role of Bottom-up and Top-down Information in Phoneme Learning

被引：0

作者：

Fourtassi, Abdellah ^{[1
]}

Schatz, Thomas ^{[1
,2
]}

Varadarajan, Balakrishnan ^{[3
]}

Dupoux, Emmanuel ^{[1
]}

机构：

[1] ENS EHESS CNRS, Lab Sci Cognit & Psycholinguist, Paris, France

[2] INRIA ENS CNRS, Sierra Project Team, Paris, France

[3] JHU, Ctr Language & Speech Proc, Baltimore, MD USA

来源：

PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 | 2014年

基金：

欧洲研究理事会;

关键词：

PERCEPTION;

D O I：

暂无

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We test both bottom-up and top-down approaches in learning the phonemic status of the sounds of English and Japanese. We used large corpora of spontaneous speech to provide the learner with an input that models both the linguistic properties and statistical regularities of each language. We found both approaches to help discriminate between allophonic and phonemic contrasts with a high degree of accuracy, although top-down cues proved to be effective only on an interesting subset of the data.

引用

页码：1 / 6

页数：6

共 50 条

[1] Relative Influence of Bottom-Up and Top-Down Attention
Mancas, Matei
ATTENTION IN COGNITIVE SYSTEMS, 2009, 5395 : 212 - 226
[2] SPEECH RECOGNITION BASED ON TOP-DOWN AND BOTTOM-UP PHONEME RECOGNITION
MATSUNAGA, S
SHIKANO, K
REVIEW OF THE ELECTRICAL COMMUNICATIONS LABORATORIES, 1986, 34 (03): : 349 - 356
[3] Learning to attend - From bottom-up to top-down
Jasso, Hector
Triesch, Jochen
ATTENTION IN COGNITIVE SYSTEMS: THEORIES AND SYSTEMS FROM AN INTERDISCIPLINARY VIEWPOINT, 2007, 4840 : 106 - +
[4] Learning to combine bottom-up and top-down segmentation
Levin, Anat
Weiss, Yair
COMPUTER VISION - ECCV 2006, PT 4, PROCEEDINGS, 2006, 3954 : 581 - 594
[5] Learning to Combine Bottom-Up and Top-Down Segmentation
Levin, Anat
Weiss, Yair
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2009, 81 (01) : 105 - 118
[6] Learning to Combine Bottom-Up and Top-Down Segmentation
Anat Levin
Yair Weiss
International Journal of Computer Vision, 2009, 81 : 105 - 118
[7] Bottom-up or top-down in dream neuroscience? A top-down critique of two bottom-up studies
Foulkes, David
Domhoff, G. William
CONSCIOUSNESS AND COGNITION, 2014, 27 : 168 - 171
[8] SPEECH RECOGNITION BASED ON TOP-DOWN AND BOTTOM-UP PHONEME RECOGNITION.
Matsunaga, Sho-ichi
Shikano, Kiyohiro
Systems and Computers in Japan, 1986, 17 (07): : 95 - 106
[9] LEARNING HISTOPATHOLOGICAL REGIONS OF INTEREST BY FUSING BOTTOM-UP AND TOP-DOWN INFORMATION
Corredor, German
Romero, Eduardo
2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2015, : 3200 - 3204
[10] From bottom-up to top-down
Johnston, Hamish
PHYSICS WORLD, 2023, 36 (08) : 35 - 37

← 1 2 3 4 5 →