Filters








13,068 Hits in 6.0 sec

Effects of word recognition errors in spoken query processing

F. Crestani
Proceedings IEEE Advances in Digital Libraries 2000  
The effects of word recognition errors (WRE) in Spoken Document Retrieval have been well studied and well reported in recent Information Retrieval (IR) literature.  ...  Much less experimental work has been devoted to studying the effects of WRE in Spoken Query Processing in IR.  ...  Acknowledgments The author wishes to thank Jim Barnett, Stephen Anderson, and Dragon Systems for generating and providing the spoken queries used in this study.  ... 
doi:10.1109/adl.2000.848368 dblp:conf/adl/Crestani00 fatcat:bpcrtatru5afjpkxckckaj3nhm

Perspectives on Information Retrieval and Speech [chapter]

James Allan
2002 Lecture Notes in Computer Science  
This hypothesis is supported by examples from TREC's SDR track, the TDT evaluation, and some work showing the impact of recognition errors on spoken queries.  ...  Several years of research have suggested that the accuracy of spoken document retrieval systems is not adversely affected by speech recognition errors.  ...  The results were somewhat surprising: even tremendous numbers of speech recognition errors in a spoken document had little impact on retrieval effectiveness.  ... 
doi:10.1007/3-540-45637-6_1 fatcat:6rcw2kcwsrgzjhzi2bnwxibcja

Review of utilizing the speech identification system for spoken queries in the Qur'an

Taufik Ridwan, Nuur Wachid Abdul Majid
2018 Jurnal Taman Vokasi  
The use of sound as input to the system to do searches in data in a text representation is called spoken query.  ...  This paper tries to conduct a discussion on the use of speech recognition systems to become spoken queries in the Qur'an data.  ...  Conclusion The results of spoken query research found the effect of the accuracy value of the speech recognition system on the back-to-back system that uses spoken queries.  ... 
doi:10.30738/jtv.v6i2.4147 fatcat:zz5h5usfnjg63nruaszvp3gsfq

Spoken query processing for interactive information retrieval

Fabio Crestani
2002 Data & Knowledge Engineering  
However, given the typical length of queries submitted to Information Retrieval systems, it is easy to imagine that the effects of word recognition errors in spoken queries must be severely destructive  ...  The experimental work reported in this paper shows that the use of classical Information Retrieval techniques for spoken query processing is robust to considerably high levels of word recognition errors  ...  The author wishes to thank Jim Barnett, Stephen Anderson, and Dragon Systems for generating and providing the spoken queries used in this study.  ... 
doi:10.1016/s0169-023x(02)00024-1 fatcat:awb5x7er4jhphg7bpmug6hdazm

Retrieval Effectiveness of Written and Spoken Queries: An Experimental Evaluation [chapter]

Heather Du, Fabio Crestani
2004 Lecture Notes in Computer Science  
If one compares written versus spoken queries, it is intuitive to think that users would issue longer spoken queries than written ones, due to the ease of speech. Is this in fact the case in reality?  ...  Also, if this is the case, would longer spoken queries be more effective in helping retrieving relevant document than written ones?  ...  in taking part in this experiment voluntarily.  ... 
doi:10.1007/978-3-540-25957-2_30 fatcat:iegpofcllfda7lqdpvdn3he7um

Robust Techniques for Organizing and Retrieving Spoken Documents

James Allan
2003 EURASIP Journal on Advances in Signal Processing  
We claim that the robustness of the process is because of inherent redundancy in the problem: not only are words repeated, but semantically related words also provide support.  ...  We show how document and query expansion can enhance that redundancy and make document retrieval robust to speech recognition errors.  ...  Any opinions, findings, and conclusions or recommendations expressed in this material are the author's and do not necessarily reflect those of the sponsor.  ... 
doi:10.1155/s1110865703211070 fatcat:3zkfht6oonfulfojxe4d46xpza

Open vocabulary spoken content retrieval by front-ending with spoken term detection

Tomoko Takigami, Tomoyosi Akiba
2013 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference  
How to deal with speech recognition errors and outof-vocabulary (OOV) words are common challenging problems in spoken document processing.  ...  In this work, we propose the spoken content retrieval (SCR) method that incorporates spoken term detection (STD) as the pre-processing stage.  ...  Unlike text retrieval, dealing with speech recognition errors and out-of-vocabulary (OOV) words are challenging problems in spoken document processing.  ... 
doi:10.1109/apsipa.2013.6694130 dblp:conf/apsipa/TakigamiA13 fatcat:idnkykwkrvdpdeypieepo3qjri

Experiments in spoken document retrieval using phoneme n-grams

Corinna Ng, Ross Wilkinson, Justin Zobel
2000 Speech Communication  
In spoken document retrieval, speech recognition is applied to a collection to obtain either words or subword units, such as phonemes, that can be matched against queries.  ...  Given word-based recognition, we can match queries to speech using a phoneme representation of the words, permitting us to test whether it was the recognition or the matching process that was most crucial  ...  Acknowledgments Thanks to Peter Schäuble, Eugene Munteanu and Martin Wechsler of the Swiss Institute of Technology (ETH) for providing phoneme transcriptions of the spoken document  ... 
doi:10.1016/s0167-6393(00)00024-8 fatcat:2nczktoeuzfinijo7qeihgq6i4

Effects of out of vocabulary words in spoken document retrieval (poster session)

P. C. Woodland, S. E. Johnson, P. Jourlin, K. Spärck Jones
2000 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '00  
The effects of out-of-vocabulary (OOV) items in spoken document retrieval (SDR) are investigated.  ...  The effects of OOV terms on a simple baseline IR system and on more sophisticated retrieval systems are described.  ...  The word error rate (WER); out of vocabulary word rate (OOVW); query out of vocabulary word rate (QOVW) for the 684 original query words; and size of wordlist are given in Table 1 A parallel collection  ... 
doi:10.1145/345508.345661 dblp:conf/sigir/WoodlandJJJ00 fatcat:7ddtc3awfrcofak6qnbvx4iyk4

Speech-Driven Text Retrieval: Using Target IR Collections for Statistical Language Model Adaptation in Speech Recognition [chapter]

Atsushi Fujii, Katunobu Itou, Tetsuya Ishikawa
2002 Lecture Notes in Computer Science  
Experiments using existing test collections combined with dictated queries showed the effectiveness of our method.  ...  Aiming at speech-driven text retrieval, which facilitates retrieving information with spoken queries, we propose a method to integrate speech recognition and retrieval methods.  ...  Acknowledgments The authors would like to thank the National Institute of Informatics for their support with the NTCIR collections.  ... 
doi:10.1007/3-540-45637-6_9 fatcat:622ouy5dhvd2zexa27dtkrzciq

Speech-Driven Text Retrieval: Using Target IR Collections for Statistical Language Model Adaptation in Speech Recognition [article]

Atsushi Fujii, Katunobu Itou, Tetsuya Ishikawa
2002 arXiv   pre-print
Experiments using existing test collections combined with dictated queries showed the effectiveness of our method.  ...  Aiming at speech-driven text retrieval, which facilitates retrieving information with spoken queries, we propose a method to integrate speech recognition and retrieval methods.  ...  Acknowledgments The authors would like to thank the National Institute of Informatics for their support with the NTCIR collections.  ... 
arXiv:cs/0206037v1 fatcat:6cifnoknyffdjhzns2r5lu45km

Vocal Access to a Newspaper Archive: Design Issues and Preliminary Investigation [article]

Fabio Crestani
1998 arXiv   pre-print
The results of preliminary investigation into the feasibility of such a system are also presented.  ...  This paper presents the design and the current prototype implementation of an interactive vocal Information Retrieval system that can be used to access articles of a large newspaper archive using a telephone  ...  The experimentation reported in section 5.1 was carried out with the help of Anastasios Tombros.  ... 
arXiv:cs/9812009v1 fatcat:rodwcww2o5dwvdlq24fb4lwzai

A system for spoken query information retrieval on mobile devices

E. Chang, F. Seide, H.M. Meng, Zhuoran Chen, Yu Shi, Yuk-Chi Li
2002 IEEE Transactions on Speech and Audio Processing  
This is the first work that we are aware of which evaluates spoken query based information retrieval on a commonly available and well researched text database, the Chinese news corpus used in National  ...  To compare spoken-query retrieval performance for different relevant scenarios and recognition accuracies, the benchmark queries-read verbatim by 20 speakers-were recorded simultaneously through three  ...  Fig. 2 . 2 Display shown to users after a spoken query has been processed. The query used in this illustration is: "Reform and growth in China's real estate industry."  ... 
doi:10.1109/tsa.2002.804301 fatcat:izcyym2axnbk5fpo5tbq5vd6qq

From multimedia retrieval to knowledge management

P.J. Moreno, J.-M. Van Thong, B. Logan, G.J.F. Jones
2002 Computer  
The authors suggest ways in which speech-based multimedia information retrieval technologies can evolve into full-fledged knowledge management systems in which audio, video, and images contribute as much  ...  Information retrieval systems are more sensitive to recognition errors in spoken queries than in documents derived from speech-recognition output because a short span of recorded speech lacks redundancy  ...  of speech recognition errors. 4, 5 Even with a 40 percent recognition error rate, the effectiveness of a typical document retrieval system decreases only 10 percent.  ... 
doi:10.1109/mc.2002.993772 fatcat:4o5oz2x6gvcb3b4cqpqs2w4aty

MFCC Based Speech Retrieval

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
The indexing methods, which are based on the output of phoneme recognizer, take account of speech recognition errors.  ...  This method retrieves ranked audio files containing spoken text in response to a given speech query. In this paper indexing methods are described which represent the contents of the spoken documents.  ...  It may generally be said that recognition errors may considerably affect retrieval effectiveness.  ... 
doi:10.35940/ijitee.i7550.078919 fatcat:mker26oodfbdrpdtkqzps2lgeq
« Previous Showing results 1 — 15 out of 13,068 results