|
|
|
| Query Expansion Based High Performance Chinese Voice Retrieval |
| LI Wei, WU Ji, L Ping |
| Department of Electronic Engineering,Tsinghua University,Beijing 100084 |
|
|
|
|
Abstract The aim of Chinese voice retrieval systems is to locate query texts in audio files fast and precisely. In a typical implementation of the system, voice files are recognized and stored in index. The system segments each query into a word sequence and uses the sequence to search. The mismatch between query segmentation and recognition can influence systems performance. To solve this problem, multiple segmentation results and prefix-suffix expansions have been used to broaden the original query. The retrieval process is on the basis of the expansions outputs. Query expansion generates a lot of outputs, which slows down the retrieval speed. In order to increase the systems efficiency, the Finite State Automata (FSA) is introduced to compress query expansions. And a Token-based search algorithm is used for fast search. Experimental results show that the query expansion leads the systems EER to improve about 50%~70% relatively. The FSA compresses the retrieval space, and raises the retrieval speed nearly 30 times.
|
|
Received: 25 September 2010
|
|
|
|
|
|
[1] National Institute of Standards and Technology.The Spoken Term Detection (STD) 2006 Evaluation Plan [EB/OL].[2010-7-5].http://www.itl.nist.gov/iad/mig//tests/std/2006/docs/std06-evalplan-v10.pdf
[2] Fiscus J G,Ajot J,Garofolo J S,et al.Results of the 2006 Spoken Term Detection Evaluation // Proc of the SIGIR Workshop on Search Spontaneous Conversational Speech.Amsterdam,Netherlands,2007: 51-56
[3] Mamou J,Ramabhadran B,Siohan O.Vocabulary Independent Spoken Term Detection // Proc of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.Amsterdam,Netherlands,2007: 615-622
[4] Parlak S,Saraclar M.Spoken Term Detection for Turkish Broadcast News // Proc of the IEEE International Conference on Acoustics,Speech and Signal Processing.Las Vegas,USA,2008: 5244-5247
[5] Mertens T,Schneider D.Efficient Subword Lattice Retrieval for German Spoken Term Detection // Proc of the IEEE International Conference on Acoustics,Speech and Signal Processing.Taipei,China,2009: 4885-4888
[6] Wallace R,Vogt R,Sridharan S.Spoken Term Detection Using Fast Phonetic Decoding // Proc of the IEEE International Conference on Acoustics,Speech and Signal Processing.Taipei,China,2009: 4881-4884
[7] Ni Chongjia,Liu Wenju,Xu Bo.Research on Large Vocabulary Continuous Speech Recognition System for Mandarin Chinese.Journal of Chinese Information Processing,2009,23(1): 112-123 (in Chinese)
(倪崇嘉,刘文举,徐 波.汉语大词汇量连续语音识别系统研究进展.中文信息学报,2009,23(1): 112-123)
[8] Meng Sha,Yu Peng,Seide F,et al.A Study of Lattice-Based Spoken Term Detection for Chinese Spontaneous Speech // Proc of the IEEE Workshop on Automatic Speech Recognition and Understanding.Kyoto,Japan,2007: 635-640
[9] Meng Sha,Liu Jia.Out-of-Vocabulary Issue in Chinese Spoken Term Detection and a Two-Stage Chinese Speech Retrieval Method.Journal of Chinese Information Processing,2009,23(6): 91-97 (in Chinese)
(孟 莎,刘 加.汉语语音检索的集外词问题与两阶段检索方法.中文信息学报,2009,23(6): 91-97)
[10] Liu Hongzhi. Research on Chinese Word Segmentation Techniques.Computer Development Applications,2010,23(3): 1-3 (in Chinese)
(刘红芝.中文分词技术的研究.电脑开发与应用,2010,23(3): 1-3)
[11] Hopcroft J E,Motwani R,Ullman J D.Introduction to Automata Theory,Languages,and Computation.2nd Edition.New Jersey,USA: Addison-Wesley,2001
[12] Wan Jiancheng,Yang Chunhua.An Algorithm Model of Word Omni-Segmentation for Written Chinese.Mini-Micro Systems,2003,24(7): 1247-1251 (in Chinese)
(王建成,杨春花.书面汉语的全切分分词算法模型.小型微型计算机系统,2003,24(7): 1247-1251)
[13] Li Wei,Wu Ji,Wang Zhiguo.Fast Lattice Generation Algorithm.Journal of Tsinghua University (Science and Technology),2009,49(SI): 1254-1257 (in Chinese)
(李 伟,吴 及,王智国.一种快速的语音识别词图生成算法.清华大学学报(自然科学版),2009,49(SI): 1254-1257)
[14] Martin A,Doddington G,Kamm T,et al.The DET Curve in Assessment of Detection Task Performance // Proc of the 5th European Conference on Speech Communication and Technology.Rhodes,Greece,1997: 1895-1898
[15] Griaule Biometrics.Equal Error Rate (EER) [EB/OL].[2011-2-17]. |
|
|
|
2011, Vol. 24 
