Sciweavers

1146 search results - page 112 / 230
» Modeling durations of syllables using neural networks
Sort
View
ICASSP
2011
IEEE
14 years 10 months ago
A multi-stream ASR framework for BLSTM modeling of conversational speech
We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
Martin Wöllmer, Florian Eyben, Björn Sch...
ESANN
2008
15 years 7 months ago
A Method for Time Series Prediction using a Combination of Linear Models
This paper presents a new approach for time series prediction using local dynamic modeling. The proposed method is composed of three blocks: a Time Delay Line that transforms the o...
David Martínez-Rego, Oscar Fontenla-Romero,...
BMCBI
2008
136views more  BMCBI 2008»
15 years 6 months ago
A comparison of machine learning algorithms for chemical toxicity classification using a simulated multi-scale data model
Background: Bioactivity profiling using high-throughput in vitro assays can reduce the cost and time required for toxicological screening of environmental chemicals and can also r...
Richard Judson, Fathi Elloumi, R. Woodrow Setzer, ...
ICANN
2005
Springer
15 years 12 months ago
Modelling Path Integrator Recalibration Using Hippocampal Place Cells
Abstract. The firing activities of place cells in the rat hippocampus exhibit strong correlations to the animal’s location. External (e.g. visual) as well as internal (proprioce...
Thomas Strösslin, Ricardo Chavarriaga, Denis ...
ISNN
2009
Springer
16 years 29 days ago
A New Instance-Based Label Ranking Approach Using the Mallows Model
In this paper, we introduce a new instance-based approach to the label ranking problem. This approach is based on a probability model on rankings which is known as the Mallows mode...
Weiwei Cheng, Eyke Hüllermeier