Sciweavers

INFOCOM
2011
IEEE
13 years 4 months ago
Feasibility and optimization of delay guarantees for non-homogeneous flows in IEEE 802.11 WLANs
—Due to the rapid growth of real-time applications and the ubiquity of IEEE 802.11 MAC as a layer-2 protocol for wireless local area networks (WLANs), it is of increasing interes...
Yan Gao, Chee Wei Tan, Ying Huang, Zheng Zeng, P. ...
ICASSP
2011
IEEE
13 years 4 months ago
Structured Output Layer neural network language model
This paper introduces a new neural network language model (NNLM) based on word clustering to structure the output vocabulary: Structured Output Layer NNLM. This model is able to h...
Hai Son Le, Ilya Oparin, Alexandre Allauzen, Jean-...
ICASSP
2011
IEEE
13 years 4 months ago
Extensions of recurrent neural network language model
We present several modifications of the original recurrent neural network language model (RNN LM). While this model has been shown to significantly outperform many competitive l...
Tomas Mikolov, Stefan Kombrink, Lukas Burget, Jan ...
ICASSP
2011
IEEE
13 years 4 months ago
Cosparse analysis modeling - uniqueness and algorithms
In the past decade there has been a great interest in a synthesis-based model for signals, based on sparse and redundant representations. Such a model assumes that the signal of i...
Sangnam Nam, Michael E. Davies, Michael Elad, R&ea...
ICASSP
2011
IEEE
13 years 4 months ago
Modeling temporal correlations in content fingerprints
Previous analysis of content fingerprints has mainly focused on the case of independent and identically distributed fingerprints. Practical fingerprints, however, exhibit corre...
Avinash L. Varna, Min Wu
ICASSP
2011
IEEE
13 years 4 months ago
Automatic speech recognition using Hidden Conditional Neural Fields
Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...
Yasuhisa Fujii, Kazumasa Yamamoto, Seiichi Nakagaw...
ICASSP
2011
IEEE
13 years 4 months ago
A simple music/voice separation method based on the extraction of the repeating musical structure
Repetition is a core principle in music. This is especially true for popular songs, generally marked by a noticeable repeating musical structure, over which the singer performs va...
Zafar Rafii, Bryan Pardo
ICASSP
2011
IEEE
13 years 4 months ago
Non-linear tagging models with localist and distributed word representations
Distributed representations of words are attractive since they provide a means for measuring word similarity. However, most approaches to learning distributed representations are ...
Sumit Chopra, Srinivas Bangalore
ICASSP
2011
IEEE
13 years 4 months ago
High accurate model-integration-based voice conversion using dynamic features and model structure optimization
This paper combines a parameter generation algorithm and a model optimization approach with the model-integration-based voice conversion (MIVC). We have proposed probabilistic int...
Daisuke Saito, Shinji Watanabe, Atsushi Nakamura, ...
ICASSP
2011
IEEE
13 years 4 months ago
A hierarchical generative model for Generic Audio Document Categorization
In this paper, we call the pattern classification problem that consists in assigning a category label to a long audio signal based on its semantic content as Generic Audio Documen...
Zhi Zeng, Shuwu Zhang