SPEECH RECOGNITION BASED ON TOP-DOWN AND BOTTOM-UP PHONEME RECOGNITION.

被引：0

作者：

Matsunaga, Sho-ichi ^{[1
]}

Shikano, Kiyohiro ^{[1
]}

机构：

[1] NTT, Musashino, Jpn, NTT, Musashino, Jpn

来源：

Systems and Computers in Japan | 1986年 / 17卷 / 07期

关键词：

COMPUTER METATHEORY - Programming Theory - COMPUTERS; DIGITAL - Special Purpose Application;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

This paper discusses a speech recognition system which integrates the top-down and bottom-up phoneme recognitions. The system is based on the recognition of phonemes, where the top-down and bottom-up processings are combined using a table called a blackboard. In the proposed system, the linguistic processing and the acoustic processing are structured hierarchically. The two parts are combined through the black-board, avoiding duplicated processings in the same environment. It was observed that the recognition performance by the traditional top-down processing time is decreased to one-half or one-third in word recognition and less than one-fourth in minimal phrase recognition.

引用

页码：95 / 106

共 50 条

[21] The ChPT: top-down and bottom-up
Kampf, Karol
[J]. JOURNAL OF HIGH ENERGY PHYSICS, 2021, 2021 (12)
[22] Top-down and bottom-up assessments
Hackett, Janine
[J]. BRITISH JOURNAL OF OCCUPATIONAL THERAPY, 2010, 73 (04) : 189 - 189
[23] Cortical integration of bottom-up, top-down and horizontal information in biological motion recognition
Das, S
Finkel, LH
[J]. 1ST INTERNATIONAL IEEE EMBS CONFERENCE ON NEURAL ENGINEERING 2003, CONFERENCE PROCEEDINGS, 2003, : 75 - 78
[24] Cost-Sensitive Top-Down/Bottom-Up Inference for Multiscale Activity Recognition
Amer, Mohamed R.
Xie, Dan
Zhao, Mingtian
Todorovic, Sinisa
Zhu, Song-Chun
[J]. COMPUTER VISION - ECCV 2012, PT IV, 2012, 7575 : 187 - 200
[25] Fusing Bottom-up and Top-down Pathways in Neural Networks for Visual Object Recognition
Zheng, Yuhua
Meng, Yan
Jin, Yaochu
[J]. 2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
[26] Spatial-Temporal Bottom-Up Top-Down Attention Model for Action Recognition
Wang, Jinpeng
Ma, Andy J.
[J]. IMAGE AND GRAPHICS, ICIG 2019, PT I, 2019, 11901 : 81 - 92
[27] „Bottom-up statt Top-down“
[J]. Der Freie Zahnarzt, 2023, 67 (12) : 21 - 23
[28] A Gestaltist approach to contour-based object recognition: Combining bottom-up and top-down cues
Teo, Ching L.
Fermueller, Cornelia
Aloimonos, Yiannis
[J]. INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2015, 34 (4-5): : 627 - 652
[29] The roles of bottom-up and top-down information in the recognition of reduced speech: Evidence from listeners with normal and impaired hearing
Janse, Esther
Ernestus, Mirjam
[J]. JOURNAL OF PHONETICS, 2011, 39 (03) : 330 - 343
[30] PHONEMIC RESTORATION - INSIGHTS INTO TOP-DOWN AND BOTTOM-UP PROCESSING OF SPEECH
SAMUEL, AG
[J]. BULLETIN OF THE PSYCHONOMIC SOCIETY, 1979, 14 (04) : 261 - 261

← 1 2 3 4 5 →