1,720,975 research outputs found
Experiments on Hiwire database using Denoising and Adaptation with an hybrid HMM-ANN Model
No full text
Parallel implementation of Artificial Neural Network training for speech recognition
Full text linkIn this paper we describe the implementation of a complete ANN training procedure using the block
mode back-propagation learning algorithm for sequential patterns – such as the observation feature vectors
of a speech recognition system – exploiting the high performance SIMD architecture of GPU using
CUDA and its C-like language interface. We also compare the speed-up obtained implementing the training
procedure only taking advantage of the multi-thread capabilities of multi-core processors. In our
implementation we take into account all the peculiar aspects of training large scale sequential patterns,
in particular, the re-segmentation of the training sentences, the block size for the feed-forward and for
the back-propagation steps, and the transfer of huge amount of data from host memory to the GPU card.
Our approach has been tested by training acoustic models for large vocabulary speech recognition
tasks, showing a six times reduction of the time required to train real-world large size networks with
respect to an already optimized implementation using the Intel MKL libraries.
Thanks to these optimizations and to the support of the GPU, the training time for language having a
huge set of training sentences (about one million for Italian) can be reduced from approximately a month
to 5 days
Multi source neural networks based on fixed and multiple resolution analysis for speech recognition
No full textThis paper reports the results obtained by an Automatic Speech Recognition system when MFCCs, J-RASTA Perceptual Linear Prediction Coefficients (J-Rasta PLP) and energies from a Multi Resolution Analysis (MRA) tree of filters are used as input features to a hybrid system consisting of a Neural Network (NN) which provides observation probabilities for a network of Hidden Markov Models (HMM). Furthermore, the paper compares the performance of the system when various combinations of these features are used showing a WER reduction of 20% w.r.t. the use of J-Rasta PLP coefficients, when J-Rasta PLP coefficients are combined with the energies computed at the output of the leaves of an MRA filter tree. Such a combination is practically feasible thanks to the use of a NN architecture designed to integrate multiple features, exploiting the NN capability of mixing several input parameters without any assumption about their stochastical independence. Recognition is performed on a very large test set including many speakers uttering proper names from different locations of the Italian public telephone network
Adaptation of Hybrid ANN/HMM Models using Linear Hidden Transformations and Conservative Training
Full text link- …
