MULTI-LEVEL ADAPTIVE NETWORKS IN TANDEM AND HYBRID ASR SYSTEMS

被引：0

作者：

Bell, Peter ^{[1
]}

Swietojanski, Pawel ^{[1
]}

Renals, Steve ^{[1
]}

机构：

[1] Univ Edinburgh, Ctr Speech Technol Res, Edinburgh EH8 9AB, Midlothian, Scotland

来源：

2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2013年

基金：

英国工程与自然科学研究理事会;

关键词：

deep neural networks; tandem; hybrid; MLAN; TED; BBC;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper we investigate the use of Multi-level adaptive networks (MLAN) to incorporate out-of-domain data when training large vocabulary speech recognition systems. In a set of experiments on multi-genre broadcast data and on TED lecture recordings we present results using of out-of-domain features in a hybrid DNN system and explore tandem systems using a variety of input acoustic features. Our experiments indicate using the MLAN approach in both hybrid and tandem systems results in consistent reductions in word error rate of 5-10% relative.

引用

页码：6975 / 6979

页数：5

共 50 条

[11] FRAME-LEVEL SPECAUGMENT FOR DEEP CONVOLUTIONAL NEURAL NETWORKS IN HYBRID ASR SYSTEMS
Li, Xinwei
Zhang, Yuanyuan
Zhuang, Xiaodan
Liu, Daben
2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT), 2021, : 209 - 214
[12] Multi-level metacognition for adaptive behavior
Conn, Marvin
M'Bale, Kenneth
Josyula, Darsana
BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES, 2018, 26 : 174 - 183
[13] ADAPTIVE FILTERING AND IDENTIFICATION OF MULTI-LEVEL TIME VARYING SYSTEMS.
Duan, G.R.
Deng, Z.L.
Advances in modelling & simulation, 1987, 6 (04): : 6 - 16
[14] Multi-level modeling for hybrid manufacturing systems using Arena and MATLAB
Liang, Shuang
Yao, Xifan
WMSO: 2008 INTERNATIONAL WORKSHOP ON MODELLING, SIMULATION AND OPTIMIZATION, PROCEEDINGS, 2009, : 155 - +
[15] Multi-level Parallelization for Hybrid ACO
Abdelkafi, Omar
Lepagnot, Julien
Idoumghar, Lhassane
SWARM INTELLIGENCE BASED OPTIMIZATION (ICSIBO 2014), 2014, 8472 : 60 - 67
[16] MLSNET: RESOURCE-EFFICIENT ADAPTIVE INFERENCE WITH MULTI-LEVEL SEGMENTATION NETWORKS
Yokoo, Shuhei
Iizuka, Satoshi
Fukui, Kazuhiro
2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2019, : 1510 - 1514
[17] Adaptive Synchronization Control with Multi-level Buffer in Wireless Multimedia Sensor Networks
Zhao, Guotao
Ma, Huadong
Sun, Yan
Luo, Hong
Liu, Liang
2012 IEEE 8TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING IN SENSOR SYSTEMS (DCOSS), 2012, : 50 - 57
[18] Multi-level systems security and interoperability between differently classified networks
Burns, JG
SENSORS, C31, INFORMATION, AND TRAINING TECHNOLOGIES FOR LAW ENFORCEMENT, 1999, 3577 : 188 - 199
[19] Multi-level Dense Capsule Networks
Phaye, Sai Samarth R.
Sikka, Apoorva
Dhall, Abhinav
Bathula, Deepti R.
COMPUTER VISION - ACCV 2018, PT V, 2019, 11365 : 577 - 592
[20] Efficiently Supporting Adaptive Multi-Level Serializability Models in Distributed Database Systems
Zhao, Zhanhao
SIGMOD '21: PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2021, : 2908 - 2910

← 1 2 3 4 5 →