1 |
A Multimodal User Interface for an Assistive Robotic Shopping Cart
|
|
|
|
BASE
|
|
Show details
|
|
2 |
A Multimodal User Interface for an Assistive Robotic Shopping Cart
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Sociolinguistic Features for Author Gender Identification: From Qualitative Evidence to Quantitative Analysis
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Sociolinguistic Features for Author Gender Identification:From Qualitative Evidence to Quantitative Analysis.
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Stance Classification in Texts from Blogs on the 2016 British Referendum
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Investigating Cross-lingual Multi-level Adaptive Networks: The Importance of the Correlation of Source and Target Languages
|
|
|
|
In: http://infoscience.epfl.ch/record/223756 (2016)
|
|
Abstract:
The multi-level adaptive networks (MLAN) technique is a cross-lingual adaptation framework where a bottleneck (BN) layer in a deep neural network (DNN) trained in a source lan- guage is used for producing BN features to be exploited in a second DNN in a target language. We investigate how the correlation (in the sense of phonetic similarity) of the source and target languages and the amount of data of the source language affect the efficiency of the MLAN schemes. We experiment with three different scenarios using, i) French, as a source language uncorrelated to the target language, ii) Ukrainian, as a source language correlated to the target one and finally iii) English as a source language uncorrelated to the target language using a relatively large amount of data in respect to the other two scenarios. In all cases Russian is used as target language. GLOBALPHONE data is used, except for English, where a mixture of LIBRISPEECH, TEDLIUM and AMIDA is available. The results have shown that both of these two factors are important for the MLAN schemes. Specifically, on the one hand, when a modest amount of data from the source language is used, the correlation of the source and target languages is very important. On the other hand, the correlation of the two languages seems to be less important when a relatively large amount of data, from the source language, is used. The best performance in word error rate (WER), was achieved when the English language was used as the source one in the multi-task MLAN scheme, achieving a relative improvement of 9.4% in respect to the baseline DNN model.
|
|
URL: http://infoscience.epfl.ch/record/223756 https://infoscience.epfl.ch/record/223756/files/Lazaridis_IWSLT_2016.pdf
|
|
BASE
|
|
Hide details
|
|
8 |
Evaluation and Sociolinguistic Analysis of Text Features for Gender and Age Identification
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Age Identification of Twitter Users:Classification Methods and Sociolinguistic Analysis
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Using Sociolinguistic Inspired Features for Gender Classification of Web Users
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Wavelet basis selection for enhanced speech parametrization in speaker verification
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Joint Spatial-Spectral Feature Space Clustering for Speech Activity Detection from ECoG Signals
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Joint Spatial-Spectral Feature Space Clustering for Speech Activity Detection from ECoG Signals
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Improving phone duration modelling using support vector regression fusion
|
|
|
|
In: ISSN: 0167-6393 ; EISSN: 1872-7182 ; Speech Communication ; https://hal.archives-ouvertes.fr/hal-00699049 ; Speech Communication, Elsevier : North-Holland, 2010, 53 (1), pp.85. ⟨10.1016/j.specom.2010.07.005⟩ (2010)
|
|
BASE
|
|
Show details
|
|
|
|