| 1 |
Approximating Probabilistic Models as Weighted Finite Automata
|
|
|
|
In: Computational Linguistics, Vol 47, Iss 2, Pp 221-254 (2021) (2021)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Voice Signatures
|
|
|
|
In: http://www.research.att.com/~zak/./is-asru03.ps (2003)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Weighted finite-state transducers in speech recognition
|
|
|
|
In: http://www.cs.toronto.edu/~gpenn/csc2518/mohri-pereira-riley02.pdf (2002)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Weighted Finite-State Transducers in Speech Recognition
|
|
|
|
In: http://www.cs.mun.ca/~harold/Courses/Old/Ling6800.W06/Diary/Mohri02Weighted.pdf (2001)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Weighted Finite-State Transducers in Speech Recognition
|
|
|
|
In: http://isca-speech.org/archive_open/archive_papers/asr2000/asr0_097.pdf (2000)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Weighted Finite-State Transducers in Speech Recognition
|
|
|
|
In: http://isca-speech.org/archive_open/archive_papers/asr2000/asr0_097_1.pdf (2000)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Integrated Context-Dependent Networks in Very Large Vocabulary Speech Recognition
|
|
|
|
In: http://www.research.att.com/~mohri/postscript/hclg.ps (1999)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Full Expansion Of Context-Dependent Networks In Large Vocabulary Speech Recognition
|
|
|
|
In: http://www.research.att.com/~mohri/postscript/icassp.ps (1998)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Network Optimizations for Large Vocabulary Speech Recognition
|
|
|
|
In: http://www.research.att.com/~mohri/postscript/spc.ps (1998)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Weighted Determinization and Minimization for Large Vocabulary Speech Recognition
|
|
|
|
In: http://www.clsp.jhu.edu/ws97/pronunciation/riley/detmin.ps (1997)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Pre-Initialized Composition For Large-Vocabulary Speech Recognition
|
|
|
|
In: http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/41410.pdf
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Article Submitted to Computer Speech and Language Weighted FiniteState Transducers in Speech Recognition
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
A generalized composition algorithm for weighted finite-state transducers
|
|
|
|
In: http://cs.nyu.edu/%7Eallauzen/pdf/is2009.pdf
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Web Derived Pronunciations for Spoken Term Detection Dogan Can ∗ Bo˘gaziçi University
|
|
|
|
In: http://www.clsp.jhu.edu/~arnab/pubs/sigir09-p83-webpron4std.pdf
|
|
Abstract:
Indexing and retrieval of speech content in various forms such as broadcast news, customer care data and on-line media has gained a lot of interest for a wide range of applications, from customer analytics to on-line media search. For most retrieval applications, the speech content is typically first converted to a lexical or phonetic representation using automatic speech recognition (ASR). The first step in searching through indexes built on these representations is the generation of pronunciations for named entities and foreign language query terms. This paper summarizes the results of the work conducted during the 2008 JHU Summer Workshop by the Multilingual Spoken Term Detection team, on mining the web for pronunciations and analyzing their impact on spoken term detection. We will first present methods to use the vast amount of pronunciation information available on the Web, in the form of IPA and ad-hoc transcriptions. We describe techniques for extracting candidate pronunciations from Web pages and associating them with orthographic words, filtering out poorly extracted pronunciations, normalizing IPA pronunciations to better conform to a common transcription standard, and generating phonemic representations from ad-hoc transcriptions. We then present an analysis of the effectiveness of using these pronunciations to represent Out-Of-Vocabulary (OOV) query terms on the performance of a spoken term detection (STD) system. We will provide comparisons of Web pronunciations against automated techniques for pronunciation generation as well as pronunciations generated by human experts. Our results Authors listed in alphabetical order
|
|
URL: http://www.clsp.jhu.edu/~arnab/pubs/sigir09-p83-webpron4std.pdf
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.54
|
|
BASE
|
|
Hide details
|
|
|
| 15 |
Direct Construction of Compact Context-Dependency Transducers From Data
|
|
|
|
In: http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/36834.pdf
|
|
BASE
|
|
Show details
|
|
|
| 16 |
Stochastic pronunciation modelling from hand-labelled phonetic
|
|
|
|
In: http://mi.eng.cam.ac.uk/reports/svr-ftp/nock_specom99.pdf
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Direct Construction of Compact Context-Dependency Transducers From Data
|
|
|
|
In: http://www-i6.informatik.rwth-aachen.de/publications/download/671/RybachDavidRileyMichael--DirectConstructionofCompactContext-DependencyTransducersFromData--2010.pdf
|
|
BASE
|
|
Show details
|
|
|
| 18 |
J" Compilation of Weighted Finite-State Transducers from Decision Trees
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
