10,589 Hits in 4.6 sec

New techniques for open-vocabulary spoken document retrieval

Martin Wechsler, Eugen Munteanu, Peter Schäuble
1998 Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '98  
This paper presents four novel techniques for open-vocabulary spoken document retrieval: a method to detect slots that possibly contain a query feature; a method to estimate occurrence probabilities; a  ...  These four techniques have been evaluated using the TREC-6 spoken document retrieval test collection to determine the improvements in retrieval e ectiveness with respect to a baseline retrieval method.  ...  In the case of spoken documents, these techniques can be viewed as a valuable add-on to the out-ofvocabulary problem in word-recognition based retrieval.  ... 
doi:10.1145/290941.290950 dblp:conf/sigir/WechslerMS98 fatcat:xv22n2oxlban3iar2k7voup4ti

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  ...  Cambridge University projects The Video Mail Retrieval (VMR) and Multimedia Document Retrieval (MDR) projects at Cambridge University explored a variety of techniques for retrieving spoken documents.  ...  MDR, the successor to VMR, focused on developing effective techniques for information retrieval from large collections of news broadcasts. 3 The MDR project used the Hidden Markov Model Tool Kit large-vocabulary  ... 
doi:10.1109/mc.2002.993772 fatcat:4o5oz2x6gvcb3b4cqpqs2w4aty

Retrieving spoken documents by combining multiple index sources

G. J. F. Jones, J. T. Foote, K. Spärck Jones, S. J. Young
1996 Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '96  
This paper presents domain-independent methods of spoken document retrieval.  ...  Di erent w ays of combining them are investigated, and it is shown that the best of these can increase retrieval average precision for a speakerindependent retrieval system to 85% of that achieved for  ...  The authors would like to thank David James for useful discussions, David Pye and Phil Woodland for word-external acoustic models, Julian Odell for the word-internal and language models, and Kate Knill  ... 
doi:10.1145/243199.243208 dblp:conf/sigir/JonesFJY96 fatcat:wp7tiy52wfbb7agrz7rpcgi43u

MFCC Based Speech Retrieval

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.  ...  This paper presents an approach for speech retrieval. The feature being used in this approach is MFCC.  ...  We can use N-gram approach to index the phoneme strings extracted from the speech documents. In this approach query vocabulary is unrestricted so it leads to the open vocabulary retrieval.  ... 
doi:10.35940/ijitee.i7550.078919 fatcat:mker26oodfbdrpdtkqzps2lgeq

Robust spoken document retrieval methods for misrecognition and out-of-vocabulary keywords

Hiromitsu Nishizaki, Seiichi Nakagawa
2004 Systems and Computers in Japan  
This paper describes a Japanese spoken document retrieval (SDR) system that is robust for Out-of-Vocabulary (OOV) words.  ...  Evaluation results show that the proposed technique is quite effective in robustly retrieving spoken documents.  ...  New techniques for open-vocabulary spoken document retrieval. In Proc. of ACM SIGIR'98, pp. 20-27, 1998. [13] Kenney Ng and Victor W. Zue. Subword-based approaches for spoken document retrieval.  ... 
doi:10.1002/scj.10697 fatcat:liynm3th55hkpmexm7ovomr7qi

Improving Keyword Recognition of Spoken Queries by Combining Multiple Speech Recognizer's Outputs for Speech-driven WEB Retrieval Task

2005 IEICE transactions on information and systems  
In addition, for investigating the effects on the retrieval performance in vocabulary size of the language model, we prepared two kinds of language models: the one's vocabulary size was 20,000, the other's  ...  We experimentally evaluated the techniques of combining outputs of multiple LVCSR models in recognition of spoken queries.  ...  Katsunobu Itoh (Nagoya University) for providing the trigram and bigram language models with 60,000 vocabulary size.  ... 
doi:10.1093/ietisy/e88-d.3.472 fatcat:jrjmblechbgyjgdkayojwpl5cy

Speech search

Gareth J.F. Jones
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
Although text information retrieval techniques form a core technology for speech search, speech search generally involves confronting issues less likely to arise in the text domain, such as high levels  ...  Speech search is concerned with the retrieval of spoken content from archives of speech or multimedia materials.  ...  Document Retrieval task for broadcast news, and interview retrieval in the CLEF CL-SR task. • Oveview of speech technologies for spoken content indexing, including methods for standard large vocabulary  ... 
doi:10.1145/2600428.2602293 dblp:conf/sigir/Jones14 fatcat:wegvdptefnftnmbgnc3dx5bxuu

Speech Retrieval [chapter]

Ciprian Chelba, Timothy J. Hazen, Bhuvana Ramabhadran, Murat Saraçlar
2011 Spoken Language Understanding  
In this chapter we discuss the retrieval and browsing of spoken audio documents.  ...  by inadequate statistical models or out-of-vocabulary words.  ...  For example, the out-of-vocabulary (OOV) rate for a recognizer's vocabulary on new previously unseen data is often measured.  ... 
doi:10.1002/9781119992691.ch15 fatcat:o36ulm7kh5dxvhm6alb4yz3qvy

Mandarin–English Information (MEI): investigating translingual speech retrieval

Helen M. Meng, Berlin Chen, Sanjeev Khudanpur, Gina-Anne Levow, Wai-Kit Lo, Douglas Oard, Patrick Schone, Karen Tang, Hsin-min Wang, Jianqiang Wang
2004 Computer Speech and Language  
Our system accepts an entire English news story (text) as query, and retrieves relevant Chinese broadcast news stories (audio) from the document collection.  ...  This paper describes the Mandarin-English Information (MEI) project, where we investigated the problem of cross-language spoken document retrieval (CL-SDR), and developed one of the first English-Chinese  ...  We thank the Linguistic Data Consortium for providing the TDT Corpora.  ... 
doi:10.1016/j.csl.2003.09.003 fatcat:ixr4gkjaqrhs7b7gkrabq7p3ca

Is speech recognition becoming mainstream?

S. Srinwasan, E. Brown
2002 Computer  
Subsequently, information retrieval techniques applied to the transcript create an index with time offsets into the audio.  ...  Her group is responsible for multimedia information retrieval and content protection technologies.  ... 
doi:10.1109/mc.2002.993769 fatcat:xb2sx2evlvhkbj4vcg5zzkx7l4

Spoken content retrieval

Joachim Kohler, Martha Larson, Franciska de Jong, Wessel Kraaij, Roeland Ordelman
2008 SIGIR Forum  
At the workshop, talks and posters were presented covering a wide range of topics including vocabulary independent search, spoken term detection, combination of models/indexes, use of speech recognition  ...  The workshop concluded with a panel discussion, whose goal it was to identify future research directions for speech retrieval.  ...  The complete proceedings of SSCS 2008 [2] is available online. 16 Invited Presentations SSCS 2008 opened with a keynote entitle Query-by-Example Spoken Document Retrieval by Haizhou Li of Institute  ... 
doi:10.1145/1480506.1480518 fatcat:5bfyxsfrrrckzkjdeqkzpdkmxq

Evaluating Speech-Driven IR in the NTCIR-3 Web Retrieval Task

Atsushi Fujii, Katunobu Itou
2002 NTCIR Conference on Evaluation of Information Access Technologies  
Search topics for the Web retrieval main task were dictated by ten speakers and recorded as collections of spoken queries.  ...  Experimental results showed that a) the use of target documents for language modeling and b) enhancement of the vocabulary size in speech recognition were effective to improve the system performance.  ...  Acknowledgments The authors would like to thank the organizers of the NTCIR-3 Web retrieval task and the members of the TUT group for their support to the speech-driven retrieval subtask.  ... 
dblp:conf/ntcir/FujiiI02b fatcat:vkpwkk2lpnbjjfda2em3s6trki

Unsupervised Language Model Adaptation using Utterance-based Web Search for Clinical Speech Recognition

Robert Herms, Daniel Richter, Maximilian Eibl, Marc Ritter
2015 Conference and Labs of the Evaluation Forum  
Our approach is based on the assumption that each spoken clinical document has its own context. Hence, the recognition system is adapted for each document separately.  ...  The proposed method performs two-pass decoding whereas the first transcript is processed to queries which are used for retrieving web resources as adaptation data to build a document-specific dictionary  ...  As the number of web documents retrieved per query is almost equal for both datasets, the number of web documents per spoken document is also much higher for the training set than for the test set.  ... 
dblp:conf/clef/HermsRER15 fatcat:g2qjl2n76jarney3s7jgfgnkvu

A Method for Open-Vocabulary Speech-Driven Text Retrieval [article]

Atsushi Fujii, Katunobu Itou, Tetsuya Ishikawa
2002 arXiv   pre-print
While recent retrieval techniques do not limit the number of index terms, out-of-vocabulary (OOV) words are crucial in speech recognition.  ...  Aiming at retrieving information with spoken queries, we fill the gap between speech recognition and text retrieval in terms of the vocabulary size.  ...  In spoken document retrieval, an open-vocabulary method, which combines recognition methods for words and syllables in target speech documents, was also proposed (Wechsler et al., 1998) .  ... 
arXiv:cs/0206014v1 fatcat:7qqri7gldjaphibsf36eb5jehe

A method for open-vocabulary speech-driven text retrieval

Atsushi Fujii, Katunobu Itou, Tetsuya Ishikawa
2002 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - EMNLP '02  
Aiming at retrieving information with spoken queries, we fill the gap between speech recognition and text retrieval in terms of the vocabulary size.  ...  While recent retrieval techniques do not limit the number of index terms, out-ofvocabulary (OOV) words are crucial in speech recognition.  ...  In spoken document retrieval, an open-vocabulary method, which combines recognition methods for words and syllables in target speech documents, was also proposed (Wechsler et al., 1998) .  ... 
doi:10.3115/1118693.1118718 dblp:conf/emnlp/FujiiII02 fatcat:hmpwp2pr75grnm2opnophptxfy
« Previous Showing results 1 — 15 out of 10,589 results