Sciweavers

14 search results - page 3 / 3
» Lattice-based unsupervised acoustic model training
Sort
View
ICASSP
2010
IEEE
13 years 5 months ago
Acoustic model adaptation via Linear Spline Interpolation for robust speech recognition
We recently proposed a new algorithm to perform acoustic model adaptation to noisy environments called Linear Spline Interpolation (LSI). In this method, the nonlinear relationshi...
Michael L. Seltzer, Alex Acero, Kaustubh Kalgaonka...
ICASSP
2011
IEEE
12 years 9 months ago
A paired test for recognizer selection with untranscribed data
Traditionally, the use of untranscribed speech has been restricted to unsupervised or semi-supervised training of acoustic models. Comparison of recognizers has required labeled d...
Bhiksha Raj, Rita Singh, James Baker
ICASSP
2010
IEEE
13 years 3 months ago
Spoken language translation from parallel speech audio: Simultaneous interpretation as SLT training data
In recent work, we proposed an alternative to parallel text as translation model (TM) training data: audio recordings of parallel speech (pSp), as it occurs in any communication s...
Matthias Paulik, Alex Waibel
ICASSP
2010
IEEE
13 years 5 months ago
Investigations on ensemble based unsupervised adaptation methods
We have previously proposed unsupervised cross-validation (CV) adaptation that introduces CV into an iterative unsupervised batch mode adaptation framework to suppress the influe...
Yu Kubota, Takahiro Shinozaki, Sadaoki Furui