2011 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding 2011
DOI: 10.1109/asru.2011.6163959
|View full text |Cite
|
Sign up to set email alerts
|

Regularized subspace Gaussian mixture models for cross-lingual speech recognition

Abstract: Abstract-We investigate cross-lingual acoustic modelling for low resource languages using the subspace Gaussian mixture model (SGMM). We assume the presence of acoustic models trained on multiple source languages, and use the global subspace parameters from those models for improved modelling in a target language with limited amounts of transcribed speech. Experiments on the GlobalPhone corpus using Spanish, Portuguese, and Swedish as source languages and German as target language (with 1 hour and 5 hours of t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
46
0

Year Published

2012
2012
2020
2020

Publication Types

Select...
4
3
1

Relationship

3
5

Authors

Journals

citations
Cited by 26 publications
(47 citation statements)
references
References 19 publications
1
46
0
Order By: Relevance
“…Before discussing the results on GlobalPhone, it is important to note that the results reported in various sources (for example, [1,3,7,23]) are not directly comparable. This primarily because of the differences between LMs, which are much more significant than other differences, such as the use of MFCC vs PLP features.…”
Section: Baseline Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…Before discussing the results on GlobalPhone, it is important to note that the results reported in various sources (for example, [1,3,7,23]) are not directly comparable. This primarily because of the differences between LMs, which are much more significant than other differences, such as the use of MFCC vs PLP features.…”
Section: Baseline Resultsmentioning
confidence: 99%
“…Our setup is similar to that reported in [7]. We use German as our in-domain language and we simulate different degrees of available resources by selecting random 1 and 5 hour subsets of the total 15 hours of labeled training speech data.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…In these settings, it is possible to take advantage of transcribed data from other languages to build multilingual acoustic models [1,2]. Multilingual training with Subspace Gaussian Mixture Models [3] have also been proposed to train acoustic models [4,5].…”
Section: Introductionmentioning
confidence: 99%
“…This allows a much larger number of Gaussian components to be used by each HMM state while the total number of parameters to be estimated is typically smaller compared to conventional GMM-based acoustic models. Recent research has indicated that an SGMM acoustic model may result in more accurate speech recognition compared with its GMM counterpart, in both monolingual and multilingual settings [17]- [21]. However, in noisy environments uncompensated SGMMs suffer similar problems to conventional GMMs.…”
Section: Introductionmentioning
confidence: 99%