2015
DOI: 10.2478/aoa-2014-0045
|View full text |Cite
|
Sign up to set email alerts
|

Two-Microphone Dereverberation for Automatic Speech Recognition of Polish

Abstract: Reverberation is a common problem for many speech technologies, such as automatic speech recognition (ASR) systems. This paper investigates the novel combination of precedence, binaural and statistical independence cues for enhancing reverberant speech, prior to ASR, under these adverse acoustical conditions when two microphone signals are available. Results of the enhancement are evaluated in terms of relevant signal measures and accuracy for both English and Polish ASR tasks. These show inconsistencies betwe… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2015
2015
2016
2016

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 29 publications
0
5
0
Order By: Relevance
“…Recently, many classification methods were developed in the literature [32][33][34][35][36][37][38][39][40][41][42][43][44][45]. The artificial intelligence in diagnostics of electric machines was discussed [15], [25].…”
Section: Bayes Classifiermentioning
confidence: 99%
“…Recently, many classification methods were developed in the literature [32][33][34][35][36][37][38][39][40][41][42][43][44][45]. The artificial intelligence in diagnostics of electric machines was discussed [15], [25].…”
Section: Bayes Classifiermentioning
confidence: 99%
“…Engineers and scientists developed a great variety of feature extraction and classification methods [32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47]. Classification methods are often based on artificial intelligence.…”
Section: G Neural Network With Backpropagation Algorithmmentioning
confidence: 99%
“…The problem of classification was already discussed in literature [29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][45]. Neural networks were described in many scientific articles [37][38][39][40][41][42].…”
Section: Nearest Neighbour Classifiermentioning
confidence: 99%