USE OF GEOGRAPHICAL META-DATA IN ASR LANGUAGE AND ACOUSTIC MODELS

被引：4
|
作者：
Bocchieri, Enrico [1 ]
Caseiro, Diamantino [1 ]
机构：
[1] AT&T Res, Florham Pk, NJ 07932 USA
来源：
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2010年
关键词：
Local; language; acoustic; model; metadata; ASR; VOICE SEARCH;
D O I：
10.1109/ICASSP.2010.5495026
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
The query distribution, in the speech recognition applications of directory assistance (DA) and voice-search, depends on the customer's location. This motivates the research on query models conditioned on the user location, here denoted as local models. We describe and test our methods for the estimation of local models with various degrees of spacial "granularity", for the recognition of city-state (sub-task of DA) and for the recognition of business listings, spoken over iPhones in a nation-wide business-listing voice-search service. Our local language models improve the accuracy of city-state by 2.4% absolute (32% relative error reduction), and of voice-search by 2.2% (7% relative).
引用
收藏
页码：5118 / 5121
页数：4
相关论文
共 50 条
  • [1] Meta-data conditional language modeling
    Bacchiani, M
    Roark, B
    [J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 241 - 244
  • [2] Legislative meta-data based on semantic formal models
    Leuzi, V. Bartalesi
    Biagioli, C.
    Cappelli, A.
    Sprugnoli, R.
    Turchi, F.
    [J]. METADATA AND SEMANTICS, 2009, : 329 - +
  • [3] From educational meta-data authoring to educational meta-data management
    Papaioannou, V
    Karadimitriou, P
    Papageorgiou, A
    Karagiannidis, C
    Sampson, D
    [J]. IEEE INTERNATIONAL CONFERENCE ON ADVANCED LEARNING TECHNOLOGIES, PROCEEDINGS, 2001, : 209 - 212
  • [4] Meta-data Generation of Analysis Tools and Connection with Structured Meta-data of Datasets
    Hayashi, Teruaki
    Ohsawa, Yukio
    [J]. 2016 3RD INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND INTEGRATED NETWORKS (SPIN), 2016, : 226 - 231
  • [5] TOWARDS AN ASR APPROACH USING ACOUSTIC AND LANGUAGE MODELS FOR SPEECH ENHANCEMENT
    Nayem, Khandokar Md
    Williamson, Donald S.
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 7123 - 7127
  • [6] Taming information systems for land use: Mining the meta-data
    Sadanandal, R
    De Vries, FP
    Paiboonralt, P
    [J]. PROCEEDINGS OF THE WORLD CONGRESS OF COMPUTERS IN AGRICULTURE AND NATURAL RESOURCES, 2001, : 575 - 579
  • [7] The Use of Sense in Unsupervised Training of Acoustic Models for ASR Systems
    Singh, Rita
    Lambert, Benjamin
    Raj, Bhiksha
    [J]. 11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4, 2010, : 2938 - 2941
  • [8] Meta-data for a lot of LOD
    Rietveld, Laurens
    Beek, Wouter
    Hoekstra, Rinke
    Schlobach, Stefan
    [J]. SEMANTIC WEB, 2017, 8 (06) : 1067 - 1080
  • [9] Active and Semi-Supervised Learning in ASR: Benefits on the Acoustic and Language Models
    Drugman, Thomas
    Pylkkonen, Janne
    Kneser, Reinhard
    [J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 2318 - 2322
  • [10] Meta-data for interactive storytelling
    Reithinger, N
    Pecourt, E
    Nikolova, M
    [J]. VIRTUAL STORYTELLING: USING VIRTUAL REALITY TECHNOLOGIES FOR STORYTELLING, PROCEEDINGS, 2005, 3805 : 172 - 175
12345