Conference paper

LI Ruizhi, MALLIDI Sri Harish, PLCHOT Oldřich, BURGET Lukáš and DEHAK Najim. Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition. In: Proceedings of Interspeech 2016. San Francisco: International Speech Communication Association, 2016, pp. 2365-2369. ISBN 978-1-5108-3313-5. Available from: https://www.researchgate.net/publication/307889648_Exploiting_Hidden-Layer_Responses_of_Deep_Neural_Networks_for_Language_Recognition
Publication language:english
Original title:Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition
Title (cs):Využití odezev ze skryté vrstvy hlubokých neuronových sítí pro rozpoznávání jazyka
Pages:2365-2369
Proceedings:Proceedings of Interspeech 2016
Conference:Interspeech 2016
Place:San Francisco, US
Year:2016
URL:https://www.researchgate.net/publication/307889648_Exploiting_Hidden-Layer_Responses_of_Deep_Neural_Networks_for_Language_Recognition
ISBN:978-1-5108-3313-5
Publisher:International Speech Communication Association
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2016/li_interspeech2016_IS161584.pdf [PDF]
Files: 
+Type Name Title Size Last modified
iconli_interspeech2016_IS161584.pdf241 KB2016-09-19 17:28:27
^ Select all
With selected:
Keywords
LID, I-vector, DNN, hidden layers
Annotation
The most popular way to apply Deep Neural Network (DNN) for Language IDentification (LID) involves the extraction of bottleneck features from a network that was trained on automatic speech recognition task. These features are modeled using a classical I-vector system. Recently, a more direct DNN approach was proposed, it consists of estimating the language posteriors directly from a stacked frames input. The final decision score is based on averaging the scores for all the frames for a given speech segment. In this paper, we extended the direct DNN approach by modeling all hidden-layer activations rather than just averaging the output scores. One super-vector per utterance is formed by concatenating all hidden-layer responses. The dimensionality of this vector is then reduced using a Principal Component Analysis (PCA). The obtained reduce vector summarizes the most discriminative features for language recognition based on the trained DNNs. We evaluated this approach in NIST 2015 language recognition evaluation. The performances achieved by the proposed approach are very competitive to the classical I-vector baseline.
Abstract
The most popular way to apply Deep Neural Network (DNN) for Language IDentification (LID) involves the extraction of bottleneck features from a network that was trained on automatic speech recognition task. These features are modeled using a classical I-vector system. Recently, a more direct DNN approach was proposed, it consists of estimating the language posteriors directly from a stacked frames input. The final decision score is based on averaging the scores for all the frames for a given speech segment. In this paper, we extended the direct DNN approach by modeling all hidden-layer activations rather than just averaging the output scores. One super-vector per utterance is formed by concatenating all hidden-layer responses. The dimensionality of this vector is then reduced using a Principal Component Analysis (PCA). The obtained reduce vector summarizes the most discriminative features for language recognition based on the trained DNNs. We evaluated this approach in NIST 2015 language recognition evaluation. The performances achieved by the proposed approach are very competitive to the classical I-vector baseline.
BibTeX:
@INPROCEEDINGS{
   author = {Ruizhi Li and Harish Sri Mallidi and Old{\v{r}}ich Plchot
	and Luk{\'{a}}{\v{s}} Burget and Najim Dehak},
   title = {Exploiting Hidden-Layer Responses of Deep Neural Networks
	for Language Recognition},
   pages = {2365--2369},
   booktitle = {Proceedings of Interspeech 2016},
   year = {2016},
   location = {San Francisco, US},
   publisher = {International Speech Communication Association},
   ISBN = {978-1-5108-3313-5},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11272}
}

Your IPv4 address: 54.146.47.178
Switch to IPv6 connection

DNSSEC [dnssec]