Publication Details
Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition
Mallidi Sri Harish
Plchot Oldřich, Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Dehak Najim
LID, I-vector, DNN, hidden layers
The most popular way to apply Deep Neural Network (DNN)for Language IDentification (LID) involves the extraction ofbottleneck features from a network that was trained on automaticspeech recognition task. These features are modeled usinga classical I-vector system. Recently, a more direct DNNapproach was proposed, it consists of estimating the languageposteriors directly from a stacked frames input. The final decisionscore is based on averaging the scores for all the frames fora given speech segment. In this paper, we extended the directDNN approach by modeling all hidden-layer activations ratherthan just averaging the output scores. One super-vector per utteranceis formed by concatenating all hidden-layer responses.The dimensionality of this vector is then reduced using a PrincipalComponent Analysis (PCA). The obtained reduce vectorsummarizes the most discriminative features for languagerecognition based on the trained DNNs. We evaluated this approachin NIST 2015 language recognition evaluation. The performancesachieved by the proposed approach are very competitiveto the classical I-vector baseline.
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.
@inproceedings{BUT132601,
author="Ruizhi {Li} and Sri Harish {Mallidi} and Oldřich {Plchot} and Lukáš {Burget} and Najim {Dehak}",
title="Exploiting Hidden-Layer Responses of Deep Neural Networks for Language Recognition",
booktitle="Proceedings of Interspeech 2016",
year="2016",
pages="3265--3269",
publisher="International Speech Communication Association",
address="San Francisco",
doi="10.21437/Interspeech.2016-1584",
isbn="978-1-5108-3313-5",
url="https://www.researchgate.net/publication/307889648_Exploiting_Hidden-Layer_Responses_of_Deep_Neural_Networks_for_Language_Recognition"
}