FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W606219753> ?p ?o ?g. }

• W606219753 abstract "This thesis presents methods and results for optimizing subword detectors in continuous speech. Speech detectors are useful within areas like detection-based ASR, pronunciation training, phonetic analysis, word spotting, etc. Firstly, we propose a structure suitable for subword detection. This structure is based on the standard HMM framework, but in each detector the MFCC feature extractor and the models are trained for the specific detection problem. Our experiments in the TIMIT database validate the effectiveness of this structure for detection of phones and articulatory features. Secondly, two discriminative training techniques are proposed for detector training. The first one is a modification of Minimum Classification Error training. The second one, Minimum Detection Error training, is the adaptation of Minimum Phone Error to the detection problem. Both methods are used to train HMMs and filterbanks in the detectors, isolated or jointly. MDE has the advantage that any detection performance criterion can be optimized directly. F-score and class accuracy optimization experiments show that MDE training is superior to the MCE-based method. The optimized filterbanks reflect some acoustical properties of the detection classes. Moreover, some changes are consistent over classes with similar acoustical properties. In addition, MDE-training of filterbanks results in filters significatively different than in the standard filterbank. In fact, some filters extract information from different critical bands. Finally, we propose a detection-based automatic speech recognition system. Detectors are built with the proposed HMM-based detection structure and trained discriminatively. The linguistic merger is based on an MLP/Viterbi decoder." @default.
• W606219753 created "2016-06-24" @default.
• W606219753 creator A5024412140 @default.
• W606219753 date "2012-01-01" @default.
• W606219753 modified "2023-09-24" @default.
• W606219753 title "Design of Detectors for Automatic Speech Recognition" @default.
• W606219753 cites W110305337 @default.
• W606219753 cites W137140213 @default.
• W606219753 cites W141456524 @default.
• W606219753 cites W1490760466 @default.
• W606219753 cites W1509905243 @default.
• W606219753 cites W1524975733 @default.
• W606219753 cites W1586405805 @default.
• W606219753 cites W1593863584 @default.
• W606219753 cites W16408605 @default.
• W606219753 cites W1877570817 @default.
• W606219753 cites W193119429 @default.
• W606219753 cites W1938122300 @default.
• W606219753 cites W1961392502 @default.
• W606219753 cites W1967177300 @default.
• W606219753 cites W1979136262 @default.
• W606219753 cites W1985836220 @default.
• W606219753 cites W1990846994 @default.
• W606219753 cites W1992314141 @default.
• W606219753 cites W1994396704 @default.
• W606219753 cites W1995184477 @default.
• W606219753 cites W2002471819 @default.
• W606219753 cites W2024539680 @default.
• W606219753 cites W202593991 @default.
• W606219753 cites W203133937 @default.
• W606219753 cites W2041299350 @default.
• W606219753 cites W2060630096 @default.
• W606219753 cites W2067093722 @default.
• W606219753 cites W2077804127 @default.
• W606219753 cites W2080758042 @default.
• W606219753 cites W2090861223 @default.
• W606219753 cites W2092286949 @default.
• W606219753 cites W2097087333 @default.
• W606219753 cites W2097468589 @default.
• W606219753 cites W2099901051 @default.
• W606219753 cites W2102473096 @default.
• W606219753 cites W2102775757 @default.
• W606219753 cites W2117109565 @default.
• W606219753 cites W2118504934 @default.
• W606219753 cites W2119155265 @default.
• W606219753 cites W2119419436 @default.
• W606219753 cites W2119689163 @default.
• W606219753 cites W2120294472 @default.
• W606219753 cites W2125142492 @default.
• W606219753 cites W2125610823 @default.
• W606219753 cites W2125828495 @default.
• W606219753 cites W2127846433 @default.
• W606219753 cites W2133924365 @default.
• W606219753 cites W2135346934 @default.
• W606219753 cites W2142049426 @default.
• W606219753 cites W2143908786 @default.
• W606219753 cites W2146442261 @default.
• W606219753 cites W2147627917 @default.
• W606219753 cites W2148099973 @default.
• W606219753 cites W2148154194 @default.
• W606219753 cites W2148226542 @default.
• W606219753 cites W2151311453 @default.
• W606219753 cites W2151445288 @default.
• W606219753 cites W2152195628 @default.
• W606219753 cites W2156346614 @default.
• W606219753 cites W2157991791 @default.
• W606219753 cites W2158289097 @default.
• W606219753 cites W2158808283 @default.
• W606219753 cites W2160373860 @default.
• W606219753 cites W2163314930 @default.
• W606219753 cites W2163614729 @default.
• W606219753 cites W2163897524 @default.
• W606219753 cites W2164115090 @default.
• W606219753 cites W2166661046 @default.
• W606219753 cites W2170527457 @default.
• W606219753 cites W2243374275 @default.
• W606219753 cites W2262939877 @default.
• W606219753 cites W2399401597 @default.
• W606219753 cites W2405832053 @default.
• W606219753 cites W2405868127 @default.
• W606219753 cites W2799061466 @default.
• W606219753 cites W2949468472 @default.
• W606219753 cites W2952387069 @default.
• W606219753 cites W3127686677 @default.
• W606219753 cites W334543181 @default.
• W606219753 cites W37551777 @default.
• W606219753 cites W37868391 @default.
• W606219753 cites W54771919 @default.
• W606219753 cites W59592858 @default.
• W606219753 cites W839045117 @default.
• W606219753 cites W943204654 @default.
• W606219753 hasPublicationYear "2012" @default.
• W606219753 type Work @default.
• W606219753 sameAs 606219753 @default.
• W606219753 citedByCount "0" @default.
• W606219753 crossrefType "dissertation" @default.
• W606219753 hasAuthorship W606219753A5024412140 @default.
• W606219753 hasConcept C100515483 @default.
• W606219753 hasConcept C106131492 @default.
• W606219753 hasConcept C11413529 @default.

• next