Matches in SemOpenAlex for { <https://semopenalex.org/work/W69656834> ?p ?o ?g. }
- W69656834 abstract "For the first time in human history, large volumes of spoken audio are being broadcast, made available on the internet, archived, and monitored for surveillance every day. New technologies are urgently required to unlock these vast and powerful stores of information. Spoken Term Detection (STD) systems provide access to speech collections by detecting individual occurrences of specified search terms. The aim of this work is to develop improved STD solutions based on phonetic indexing. In particular, this work aims to develop phonetic STD systems for applications that require open-vocabulary search, fast indexing and search speeds, and accurate term detection. Within this scope, novel contributions are made within two research themes, that is, accommodating phone recognition errors and, secondly, modelling uncertainty with probabilistic scores. A state-of-the-art Dynamic Match Lattice Spotting (DMLS) system is used to address the problem of accommodating phone recognition errors with approximate phone sequence matching. Extensive experimentation on the use of DMLS is carried out and a number of novel enhancements are developed that provide for faster indexing, faster search, and improved accuracy. Firstly, a novel comparison of methods for deriving a phone error cost model is presented to improve STD accuracy, resulting in up to a 33% improvement in the Figure of Merit. A method is also presented for drastically increasing the speed of DMLS search by at least an order of magnitude with no loss in search accuracy. An investigation is then presented of the effects of increasing indexing speed for DMLS, by using simpler modelling during phone decoding, with results highlighting the trade-off between indexing speed, search speed and search accuracy. The Figure of Merit is further improved by up to 25% using a novel proposal to utilise word-level language modelling during DMLS indexing. Analysis shows that this use of language modelling can, however, be unhelpful or even disadvantageous for terms with a very low language model probability. The DMLS approach to STD involves generating an index of phone sequences using phone recognition. An alternative approach to phonetic STD is also investigated that instead indexes probabilistic acoustic scores in the form of a posterior-feature matrix. A state-of-the-art system is described and its use for STD is explored through several experiments on spontaneous conversational telephone speech. A novel technique and framework is proposed for discriminatively training such a system to directly maximise the Figure of Merit. This results in a 13% improvement in the Figure of Merit on held-out data. The framework is also found to be particularly useful for index compression in conjunction with the proposed optimisation technique, providing for a substantial index compression factor in addition to an overall gain in the Figure of Merit. These contributions significantly advance the state-of-the-art in phonetic STD, by improving the utility of such systems in a wide range of applications." @default.
- W69656834 created "2016-06-24" @default.
- W69656834 creator A5044221182 @default.
- W69656834 date "2010-01-01" @default.
- W69656834 modified "2023-09-24" @default.
- W69656834 title "Fast and accurate phonetic spoken term detection" @default.
- W69656834 cites W110431811 @default.
- W69656834 cites W114193738 @default.
- W69656834 cites W128467325 @default.
- W69656834 cites W1488355515 @default.
- W69656834 cites W1494604982 @default.
- W69656834 cites W1495147193 @default.
- W69656834 cites W1507177964 @default.
- W69656834 cites W1553339574 @default.
- W69656834 cites W1591237756 @default.
- W69656834 cites W1631260214 @default.
- W69656834 cites W1647671624 @default.
- W69656834 cites W1654514665 @default.
- W69656834 cites W183136171 @default.
- W69656834 cites W1956559956 @default.
- W69656834 cites W1977986156 @default.
- W69656834 cites W1984375608 @default.
- W69656834 cites W1999420022 @default.
- W69656834 cites W2002890640 @default.
- W69656834 cites W202593991 @default.
- W69656834 cites W2029925736 @default.
- W69656834 cites W2032118286 @default.
- W69656834 cites W2035451234 @default.
- W69656834 cites W2040226630 @default.
- W69656834 cites W2056986588 @default.
- W69656834 cites W2063614293 @default.
- W69656834 cites W2080141381 @default.
- W69656834 cites W2098841537 @default.
- W69656834 cites W2100068632 @default.
- W69656834 cites W2100506586 @default.
- W69656834 cites W2101346879 @default.
- W69656834 cites W2106067969 @default.
- W69656834 cites W2106365165 @default.
- W69656834 cites W2113410090 @default.
- W69656834 cites W2115010881 @default.
- W69656834 cites W2120929742 @default.
- W69656834 cites W2131133093 @default.
- W69656834 cites W2136440675 @default.
- W69656834 cites W2138739621 @default.
- W69656834 cites W2143331230 @default.
- W69656834 cites W2145565887 @default.
- W69656834 cites W2149998531 @default.
- W69656834 cites W2150857077 @default.
- W69656834 cites W2151284827 @default.
- W69656834 cites W2153839310 @default.
- W69656834 cites W2154087295 @default.
- W69656834 cites W2154485447 @default.
- W69656834 cites W2159436188 @default.
- W69656834 cites W2168119002 @default.
- W69656834 cites W2186490579 @default.
- W69656834 cites W23025778 @default.
- W69656834 cites W2397798422 @default.
- W69656834 cites W2441154163 @default.
- W69656834 cites W2595741664 @default.
- W69656834 cites W2612891210 @default.
- W69656834 cites W3127686677 @default.
- W69656834 cites W3196291570 @default.
- W69656834 cites W3207342693 @default.
- W69656834 cites W49437105 @default.
- W69656834 cites W2274884225 @default.
- W69656834 cites W2610919270 @default.
- W69656834 hasPublicationYear "2010" @default.
- W69656834 type Work @default.
- W69656834 sameAs 69656834 @default.
- W69656834 citedByCount "1" @default.
- W69656834 countsByYear W696568342017 @default.
- W69656834 crossrefType "dissertation" @default.
- W69656834 hasAuthorship W69656834A5044221182 @default.
- W69656834 hasConcept C105795698 @default.
- W69656834 hasConcept C121332964 @default.
- W69656834 hasConcept C124101348 @default.
- W69656834 hasConcept C138885662 @default.
- W69656834 hasConcept C154945302 @default.
- W69656834 hasConcept C165064840 @default.
- W69656834 hasConcept C199360897 @default.
- W69656834 hasConcept C23123220 @default.
- W69656834 hasConcept C2777601683 @default.
- W69656834 hasConcept C2778012447 @default.
- W69656834 hasConcept C2778707766 @default.
- W69656834 hasConcept C2781213101 @default.
- W69656834 hasConcept C28490314 @default.
- W69656834 hasConcept C33923547 @default.
- W69656834 hasConcept C41008148 @default.
- W69656834 hasConcept C41895202 @default.
- W69656834 hasConcept C49937458 @default.
- W69656834 hasConcept C61797465 @default.
- W69656834 hasConcept C62520636 @default.
- W69656834 hasConcept C75165309 @default.
- W69656834 hasConceptScore W69656834C105795698 @default.
- W69656834 hasConceptScore W69656834C121332964 @default.
- W69656834 hasConceptScore W69656834C124101348 @default.
- W69656834 hasConceptScore W69656834C138885662 @default.
- W69656834 hasConceptScore W69656834C154945302 @default.
- W69656834 hasConceptScore W69656834C165064840 @default.
- W69656834 hasConceptScore W69656834C199360897 @default.