2007 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding (ASRU) 2007
DOI: 10.1109/asru.2007.4430080
|View full text |Cite
|
Sign up to set email alerts
|

Monolingual and crosslingual comparison of tandem features derived from articulatory and phone MLPS

Abstract: In recent years, the features derived from posteriors of a multilayer perceptron (MLP), known as tandem features, have proven to be very effective for automatic speech recognition. Most tandem features to date have relied on MLPs trained for phone classification. We recently showed on a relatively small data set that MLPs trained for articulatory feature classification can be equally effective. In this paper, we provide a similar comparison using MLPs trained on a much larger data set-2000 hours of English con… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
12
0

Year Published

2010
2010
2019
2019

Publication Types

Select...
5
4

Relationship

2
7

Authors

Journals

citations
Cited by 23 publications
(12 citation statements)
references
References 21 publications
0
12
0
Order By: Relevance
“…Tandem features, based on phone posterior probability estimates, were originally proposed to improve monolingual speech recognition [11], but they have also proven effective in the cross-lingual setting. In this approach, multi-layer perceptrons (MLPs) trained using source language acoustic data of source language, are used to generate the MLP phone posterior features for the target language [12], [13], [14], [15]. As tandem acoustic features are not directly dependent on the lexicon, this approach is simple to apply.…”
Section: Introductionmentioning
confidence: 99%
“…Tandem features, based on phone posterior probability estimates, were originally proposed to improve monolingual speech recognition [11], but they have also proven effective in the cross-lingual setting. In this approach, multi-layer perceptrons (MLPs) trained using source language acoustic data of source language, are used to generate the MLP phone posterior features for the target language [12], [13], [14], [15]. As tandem acoustic features are not directly dependent on the lexicon, this approach is simple to apply.…”
Section: Introductionmentioning
confidence: 99%
“…In this approach, multi-layer perceptrons (MLPs) trained using source language acoustic data of source language, are used to generate the MLP phone posterior features for the target language [12], [13], [14], [15]. As tandem acoustic features are not directly dependent on the lexicon, this approach is simple to apply.…”
Section: Introductionmentioning
confidence: 99%
“…One of the common approach to model AFs is to estimate these features using ANNs; transform them using tandem feature extraction technique; concatenate them with the acoustic feature; and model them with HMMs [14,15,18,19]. We can adopt a similar approach for SL processing where the features representing different channels of information are extracted, concatenated…”
Section: Standard Hmm Based Approachmentioning
confidence: 99%