Search
Search Funnelback University
- Refined by:
- Date: 2006
1 -
10 of
48
search results for TALK:Vb20 24 / |u:mi.eng.cam.ac.uk
where 0
match all words and 48
match some words.
Results that match 1 of 2 words
-
MODEL-BASED TECHNIQUES FORNOISE ROBUST SPEECH RECOGNITION Mark John…
mi.eng.cam.ac.uk/~mjfg/thesis.pdf5 Jun 2006: 233.2.4 State-Based Speech Enhancement. 24. 3.3 Model-Based Techniques. 243.3.1 Linear Regression Adaptation. ... Ljm(τ ) = p(qjm(τ )|YT , M) (2.24)=. 1L(YT |M) Uj (τ )cjmbjm(y(τ ))βj (τ ). where. Uj (τ ) =. . a1j , if τ = 1N1i=2. -
JOURNAL OF IEEE TRANS. ACOUST., SPEECH, SIGNAL PROCESSING, JULY ...
mi.eng.cam.ac.uk/~mjfg/sim_SAP06.pdf22 Nov 2006: The set of parameters,Θ(sm),. 1Using this form of auxiliary function yields the same update formulae asusing the extended Baum-Welch (EBW) algorithm [24], [25]. ... Wmpem =B2D. 2m B1Dm B0β. (c)m Dm. (23). where. B2 = Σ̂m (24). -
Temporally Varying Model Parameters forLarge Vocabulary Continuous…
mi.eng.cam.ac.uk/~mjfg/sim_INTER05.pdf22 Nov 2006: ãtj = max{atj , amin} (24). whereãtj is the floored scale factor andamin is the scale floor.In this paper,amin of 0.1 was used. -
article.dvi
mi.eng.cam.ac.uk/~mjfg/rosti_CSL04.pdf22 Nov 2006: Factor analysed hidden Markov models for. speech recognition. A-V.I. Rosti , M.J.F. Gales. Cambridge University Engineering Department, Trumpington Street, Cambridge,. CB2 1PZ, UK. Abstract. Recently various techniques to improve the correlation -
Complementary System Combination andGeneration for ASR Mark Gales 20…
mi.eng.cam.ac.uk/~mjfg/mjfg_tcstar.pdf5 Jul 2006: Complementary System Selection (“Random”). • Variability to systems can be obtained by varying for example:– segmentation and clustering [3]– acoustic model decision tree [24]– acoustic model context (tri/quin-phone) [4]– ... Cambridge -
Discriminative Adaptation for Speaker Verification C. Longworth and…
mi.eng.cam.ac.uk/~mjfg/longworth_INTER06.pdf22 Nov 2006: ComponentsGMM A-GMM. EER(%) minDCF EER(%) minDCF. 128 12.17 0.5014 8.62 0.3714256 11.24 0.4704 7.88 0.3467512 11.13 0.4638 7.48 -
IEEE TRANS. ON SAP, VOL. ?, NO. ??, ????? ...
mi.eng.cam.ac.uk/~mjfg/liu_ASL07.pdf22 Nov 2006: 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. -
Joint Uncertainty Decoding for Noise Robust Speech Recognition H. ...
mi.eng.cam.ac.uk/~mjfg/liao_INTER05.pdf19 Dec 2006: Uncertainty 1 4 16 256. Clean — 33.2. SPLICENo. 24.6 20.7 17.0 12.3FE-CMLLR 16.3 15.3 12.8 13.5. -
Journal of VLSI Signal Processing manuscript No.(will be inserted ...
mi.eng.cam.ac.uk/~mjfg/layton_JVLSI07.pdf22 Nov 2006: Km(Oi, Oj ; λ(1)) (24)where Kl(Oi, Oj ; λ) is the dot-product of the log-likelihoodratios and Kc(Oi, Oj ; λ(1)), Km(Oi, Oj ; λ(1)), etc., ... than in the ML case. This is because the MMI base-line performs much better than the ML baseline -
AUGMENTED STATISTICAL MODELS FOR SPEECH RECOGNITION M.I. Layton and…
mi.eng.cam.ac.uk/~mjfg/layton_ICASSP06.pdf22 Nov 2006: HMM ML – 29.4 27.3C-Aug ML CML 24.2 –. HMM MMI – 25.3 24.8C-Aug MMI CML 23.4 –. Table 2. Classification error on the TIMIT core test ... A point of particular interest is that despite poorer statesegmentation—the sufficient statistics fix the
Search history
Recently clicked results
Recently clicked results
Your click history is empty.
Recent searches
Recent searches
Your search history is empty.