Search
Search Funnelback University
- Refined by:
- Date: 2007
1 -
10 of
28
search results for katalk:za31 24 / / / / / |u:mi.eng.cam.ac.uk
where 0
match all words and 28
match some words.
Results that match 1 of 2 words
-
Discriminative Models for Speech Recognition Mark Gales 1 February ...
mi.eng.cam.ac.uk/~mjfg/talk_ita.pdf22 Feb 2007: 3-emitting state HMMs. ClassifierTraining Componentsλ α 10 20. HMM ML – 29.4 27.3C-Aug ML CML 24.2 –. HMM MMI – 25.3 24.8C-Aug MMI CML 23.4 –. -
Recent Progress in Large Vocabulary ContinuousSpeech Recognition: An…
mi.eng.cam.ac.uk/~mjfg/icassp06_tutorial.pdf22 Feb 2007: 20. 25. 30. Cambridge UniversityEngineering Department. ICASSP 2006 Tutorial 24. Recent Progress in LVCSR: An HTK Perspective cMark Gales & Phil Woodland, 2006. ... generate a lattice when recognising the adaptation data– accumulate statistics over the -
tech.dvi
mi.eng.cam.ac.uk/~mjfg/liao_tr552.pdf21 Sep 2007: This noise robustness DBN has been used as a framework for uncertainty decoding [7, 24]. ... µ0µ. (m)2x (24). Σ(m)2y diag. {. y. x. µ0Σ. (m)2x. y. -
Unsupervised Language Model Adaptation for Mandarin…
mi.eng.cam.ac.uk/reports/svr-ftp/mrva_icslp06.pdf20 Jan 2007: Test set baseline N-gram adaptfixed weights dynamic weights. dev05bcm (BC) 25.6 24.5eval04 (BN) 14.7 14.8dev04f (BN) 6.4 6.5. ... P3 27.4 25.6 24.5 24.3 24.3. Table 3: P2, P3 stage dev05bcm CERs. -
IEEE TRANS. ON SAP, VOL. ?, NO. ??, ????? ...
mi.eng.cam.ac.uk/~mjfg/kai_ASP07.pdf23 Apr 2007: It is also interesting to compare N-Best supervisionto the standard 1-Best supervision adaptation approaches suchas iterative MLLR [24]. ... Zθ(O, H)can be simply calculated using the forward algorithm withp̃(ot|θt),. Zθ(O, H) =. θ. P (θ|M). t. -
UNSUPERVISED TRAINING FOR MANDARIN BROADCAST NEWS AND…
mi.eng.cam.ac.uk/~mjfg/wang_ICASSP07.pdf22 Jun 2007: SystemData bcmdev05. Select. ML MMI MPE. S0 — 29.2 26.7 25.3S1 — 26.1 23.3 21.8S2a — 27.7 25.9 24.7S2b CN08 27.9 25.8 ... 8S3a — 27.7 — 24.8S3b CN08 28.0 — 24.7. -
IEEE TRANS. ON SAP, VOL. ?, NO. ??, ????? ...
mi.eng.cam.ac.uk/research/projects/AGILE/publications/liu_ASL07.pdf10 Oct 2007: This sensitivity to outliers is a well known feature of the MMI criterion [24]. ... j))}. (24). Each Gaussian component is assumed to be independent of all others. -
ROTATIONAL MOTION INSENSORLESS FREEHAND 3D ULTRASOUND R. J. Housden,…
mi.eng.cam.ac.uk/reports/svr-ftp/housden_tr587.pdf5 Oct 2007: Ultrasonic Imaging, 24(1):1–12, January 2002. [14] L. Mercier, T. Langø, F. ... Ultrasound inMedicine and Biology, 24(9):1243–1270, December 1998. [18] M. O’Donnell and S. -
Discriminative Models for Speech RecognitionM.J.F. Gales Cambridge…
mi.eng.cam.ac.uk/~mjfg/mjfg_ita.pdf22 Feb 2007: Nowthe features associated with the acoustic data are. Ta(O1:T , w) = φ(O1:T ; λ) (24). ... 24] G. Saon, D. Povey, and G. Zweig, “CTS decoding improvementsat IBM,” in EARS STT workshop, St. -
UNSUPERVISED TRAINING FOR MANDARIN BROADCAST NEWS AND…
mi.eng.cam.ac.uk/research/projects/AGILE/publications/wang_ICASSP07.pdf10 Oct 2007: SystemData bcmdev05. Select. ML MMI MPE. S0 — 29.2 26.7 25.3S1 — 26.1 23.3 21.8S2a — 27.7 25.9 24.7S2b CN08 27.9 25.8 ... 8S3a — 27.7 — 24.8S3b CN08 28.0 — 24.7.
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
- Economics middle test |u:www.queens.cam.ac.uk (7) · moments ago
- endogenous retrovirus (342) · moments ago
Recent searches
Your search history is empty.