{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:51Z","timestamp":1775229771127,"version":"3.50.1"},"reference-count":88,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,12]]},"DOI":"10.1109\/asru.2009.5372952","type":"proceedings-article","created":{"date-parts":[[2010,1,13]],"date-time":"2010-01-13T15:40:58Z","timestamp":1263397258000},"page":"26-43","source":"Crossref","is-referenced-by-count":9,"title":["Voice-based information retrieval — how far are we from the text-based information retrieval ?"],"prefix":"10.1109","author":[{"given":"Lin-shan","family":"Lee","sequence":"first","affiliation":[]},{"given":"Yi-cheng","family":"Pan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367184"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/1080343.1080347"},{"key":"ref71","first-page":"625","article-title":"Hierarchical Topic Organization and Visual Presentation of Spoken Documents Using Probabilistic Latent Semantic Analysis (PLSA) for Efficient Retrieval\/Browsing Applications","author":"li","year":"2005","journal-title":"European Conference on Speech Communication and Technology"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/1031171.1031193"},{"key":"ref76","article-title":"Talking to machines (statistically speaking)","author":"young","year":"2002","journal-title":"ICSLP"},{"key":"ref77","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1109\/89.817460","article-title":"Jupiter: A telephone-based conversational interface for weather information","volume":"8","author":"seneff","year":"2000","journal-title":"IEEE Trans on Speech and Audio Processing"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1520340.1520655"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518773"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/5.880078"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00008-X"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1511821"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.06.008"},{"key":"ref33","first-page":"318","article-title":"Subword-Based Position Specific Posterior Lattices (S-PSPL) for Indexing Speech Information","author":"pan","year":"2007","journal-title":"InterSpeech"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/281250.281253"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1007\/11939993_45","article-title":"Improved large vocabulary continuous Chinese speech recognition by character-based consensus networks","author":"fu","year":"2006","journal-title":"International Symposium on Chinese Spoken Language Processing"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0152"},{"key":"ref37","first-page":"2385","article-title":"A Phonetic Search Approach to the 2006 NIST Spoken Term Detection Evaluation","author":"wallace","year":"0","journal-title":"Interspeech 2007"},{"key":"ref36","first-page":"169","article-title":"Statistics-based segment pattern lexicon: A new direction for Chinese language modeling","author":"yang","year":"1998","journal-title":"ICASSP"},{"key":"ref35","first-page":"133","article-title":"Tone-enhanced generalized character posterior probability (GCPP) for Cantonese LVCSR","author":"yao","year":"2006","journal-title":"ICASSP"},{"key":"ref34","first-page":"13","article-title":"Generalized posterior probability for minimizing verification errors at subword, word and sentence levels","author":"lo","year":"2004","journal-title":"ISCSLP"},{"key":"ref60","first-page":"2169","article-title":"Automatic extraction of key sentences from oral presentations using statistical measure based on discourse markers","author":"kitade","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref62","first-page":"1531","article-title":"Summarization of Spontaneous Conversations","author":"zhu","year":"2006","journal-title":"Proceedings of the 9th International Conference on Spoken Language Processing (Interspeech 2006)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326810"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518770"},{"key":"ref28","first-page":"629","article-title":"Towards Spoken Document Retrieval for the Enterprise: Approximate Word-Lattice Indexing with Text Indexers","author":"seide","year":"0","journal-title":"ASRU 2007"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312748"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851881"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075259"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/1119312.1119314"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref67","first-page":"1","article-title":"Automatic title generation for spoken broadcase news","author":"jin","year":"2001","journal-title":"Proc of HLT"},{"key":"ref68","first-page":"2813","article-title":"Automatic title generation for chinese spoken documents using an adaptive k nearest-neighbor approach","author":"chen","year":"2003","journal-title":"Proc in EUROSPEECH"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2008.4777866"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.918410"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219895"},{"key":"ref20","first-page":"363","article-title":"A Lattice-based Approach to Query-by-Example Spoken Term Retrieval","author":"chia","year":"0","journal-title":"SIGIR 2008"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1145\/1376616.1376656","article-title":"Approximate Embedding-Based Sequence Matching of Time Series","author":"athitsos","year":"2008","journal-title":"SIGMOD 2008"},{"key":"ref21","first-page":"2191","article-title":"Spoken Keyword Spotting via Multi-lattice alignment","author":"lin","year":"0","journal-title":"Interspeech 2008"},{"key":"ref24","first-page":"2106","article-title":"Phonetic Query Expansion for Spoken Document Retrieval","author":"mamou","year":"0","journal-title":"Interspeech 2008"},{"key":"ref23","article-title":"Speech and Sound Search on the Web: System Design and Implementation","author":"yaguchi","year":"0","journal-title":"IEEE International Conference on Computer and Information Technology 2007"},{"key":"ref26","article-title":"Towards Robust Methods for Spoken Document Retrieval","author":"ng","year":"0","journal-title":"ICSLP 1998"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345552"},{"key":"ref50","first-page":"544","article-title":"Type- II Dialogue Systems for Information Access from Unstructured Knowledge Sources","author":"pan","year":"2007","journal-title":"IEEE Automatic Speech Recognition and Understanding Workshop"},{"key":"ref51","first-page":"375","article-title":"A Multi-Modal Dialogue System for Information Navigation and Retrieval across Spoken Document Archives with Topic Hierarchies","author":"pan","year":"2005","journal-title":"Proceedings of IEEE Automatic Speech Recognition and Understanding Workshop"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220882"},{"key":"ref58","article-title":"Comparing lexical, acoustic\/prosodic, structural and discourse features for speech summarization","author":"maskey","year":"2005","journal-title":"Proc of Eurospeech 2005"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828699"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/383952.383955"},{"key":"ref55","article-title":"Advances in Automatic Text Summarization","author":"mani","year":"1999"},{"key":"ref54","first-page":"1941","article-title":"Improved Spoken Document Summarization Using Probabilistic Latent Semantic Analysis (PLSA)","author":"kong","year":"2006","journal-title":"International Conference on Acoustics Speech and Signal Processing"},{"key":"ref53","first-page":"1961","article-title":"Improved Spoken Document Retrieval with Dynamic Key Term Lexicon and Probabilistic Latent Semantic Analysis (PLSA)","author":"hsieh","year":"2006","journal-title":"International Conference on Acoustics Speech and Signal Processing"},{"key":"ref52","article-title":"Probabilistic latent semantic analysis","author":"hofmann","year":"1999","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.09.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220888"},{"key":"ref40","article-title":"Open Vocabulary Speech Recognition with Flat Hybrid Models","author":"bisiani","year":"0","journal-title":"InterSpeech 2005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367166"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.917992"},{"key":"ref14","first-page":"2393","article-title":"The SRI\/OGI 2006 Spoken Term Detection System","author":"vergyri","year":"0","journal-title":"Interspeech 2007"},{"key":"ref15","first-page":"29","article-title":"An Introduction to Voice Search","author":"wang","year":"2008","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1108\/eb026866"},{"key":"ref16","first-page":"5256","article-title":"Live Search for Mobile: Web Services by Voice on the Cellphone","author":"acero","year":"2008","journal-title":"ICASSP"},{"key":"ref81","first-page":"333","article-title":"Efficient Interactive Retrieval of Spoken Documents with Key Terms Ranked by Reinforcement Learning","author":"pan","year":"2006","journal-title":"International Conference on Spoken Language Processing"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960491"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/244130.244151"},{"key":"ref18","first-page":"2154","article-title":"Towards the Integration of Automatic Speech Recognition and Information Retrieval for Spoken Query Processing","author":"moreno-daniel","year":"0","journal-title":"Interspeech 2008"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960682"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367178"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/89.817450"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220694"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148183"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_69"},{"key":"ref5","first-page":"42","article-title":"Spoken Document Understanding and Organization","volume":"22","author":"lee","year":"2005","journal-title":"IEEE Signal Processing Magazine Special Issue on Speech Technology in Human-machine Communication"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291384"},{"key":"ref8","article-title":"The tree spoken document retrieval track: A success story","author":"garofolo","year":"2000","journal-title":"Recherched Informations Assiste par Ordinateur ContentBased Multimedia Information Access Conference"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2006.63"},{"key":"ref7","article-title":"Lattice-based search for spoken utterance retrieval","author":"saraclar","year":"2004","journal-title":"HLT"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/258525.258534"},{"key":"ref87","article-title":"A Learning-based Hybrid Tagging and Browsing Approach for Efficient Manual Image Annotation","author":"yan","year":"0","journal-title":"CVPR 2009"},{"key":"ref88","first-page":"1969","article-title":"Latent Semantic Retrieval of Personal Photos with Sparse User Annotation by Fused Image\/Speech\/Text Features","author":"fu","year":"2009","journal-title":"International Conference on Acoustics Speech and Signal Processing"},{"key":"ref9","year":"0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.802541"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277849"},{"key":"ref48","article-title":"One-pass and word-graph-based search algorithms for large vocabulary continuous mandarin speech recognition","author":"pan","year":"2001"},{"key":"ref47","first-page":"677","article-title":"Analytical Comparison between Position Specific Posterior Lattices and Confusion Networks Based on Words and Subword Units for Spoken Document Indexing","author":"pan","year":"2007","journal-title":"IEEE Automatic Speech Recognition and Understanding Workshop"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.854429"},{"key":"ref41","first-page":"5240","article-title":"Open-Vocabulary Spoken Term Detection Using Graphone-based Hybrid Recognition Systems","author":"akbacak","year":"0","journal-title":"ICASSP 2008"},{"key":"ref44","first-page":"5244","article-title":"Spoken Term Detection for Turkish Broadcast News","author":"parlak","year":"0","journal-title":"ICASSP 2008"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220694"}],"event":{"name":"Understanding (ASRU)","location":"Moreno, Italy","start":{"date-parts":[[2009,11,13]]},"end":{"date-parts":[[2009,12,17]]}},"container-title":["2009 IEEE Workshop on Automatic Speech Recognition & Understanding"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5357590\/5372876\/05372952.pdf?arnumber=5372952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,18]],"date-time":"2017-06-18T23:41:49Z","timestamp":1497829309000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5372952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,12]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/asru.2009.5372952","relation":{},"subject":[],"published":{"date-parts":[[2009,12]]}}}