Biblioteca Digital

37 resultados para CUNY Tutorial

Discriminative speaker adaptation with conditional maximum likelihood linear regression

Relevância:

10.00% 10.00%

Publicador:

On large vocabulary continuous speech recognition of highly inflectional language - Czech

Relevância:

10.00% 10.00%

Publicador:

Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling

Relevância:

10.00% 10.00%

Publicador:

Convergence of DLLR rapid speaker adaptation algorithms

Relevância:

10.00% 10.00%

Publicador:

Discriminative linear transforms for speaker adaptation

Relevância:

10.00% 10.00%

Publicador:

Speaker adaptation using lattice-based MLLR

Relevância:

10.00% 10.00%

Publicador:

Speaker adaptation for continuous density HMMs: a review

Relevância:

10.00% 10.00%

Publicador:

Segmental minimum Bayes-risk ASR voting strategies

Relevância:

10.00% 10.00%

Publicador:

CASS: A phonetically transcribed corpus of Mandarin spontaneous speech

Relevância:

10.00% 10.00%

Publicador:

Minimum risk acoustic clustering for multilingual acoustic model combination

Relevância:

10.00% 10.00%

Publicador:

Robust estimation for rapid adaptation using discounted likelihood techniques

Relevância:

10.00% 10.00%

Publicador:

On the incremental addition of regression classes for speaker adaptation

Relevância:

10.00% 10.00%

Publicador:

Discounted likelihood linear regression for rapid adaptation

Relevância:

10.00% 10.00%

Publicador:

Task dependent loss functions in speech recognition: A-star search over recognition lattices

Relevância:

10.00% 10.00%

Publicador:

Single-pass adapted training with all-pass transforms

Relevância:

10.00% 10.00%

Publicador:

«
1
2
3
»