Dual stream speech recognition using articulatory syllable models

Puurula, Antti; Compernolle, Dirk Van

doi:10.1007/s10772-010-9080-2

Cited by 7 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Depending on the likelihood function and initialization, the stationary point can remain far from a global optimum, and EM is often repeated with randomly sampled initial parameters. Other practical variants include online versions of EM [Liang and Klein, 2009] and combination with genetic algorithms [Martínez and Virtriá, 2000, Pernkopf and Bouchaffra, 2005, Puurula and Compernolle, 2010.…”

Section: Expectation Maximizationmentioning

confidence: 99%

Scalable Text Mining with Sparse Generative Models

Puurula

2016

Preprint

Self Cite

View full text Add to dashboard Cite

The information age has brought a deluge of data. Much of this is in text form, insurmountable in scope for humans and incomprehensible in structure for computers. Text mining is an expanding field of research that seeks to utilize the information contained in vast document collections. General data mining methods based on machine learning face challenges with the scale of text data, posing a need for scalable text mining methods.This thesis proposes a solution to scalable text mining: generative models combined with sparse computation. A unifying formalization for generative text models is defined, bringing together research traditions that have used formally equivalent models, but ignored parallel developments. This framework allows the use of methods developed in different processing tasks such as retrieval and classification, yielding effective solutions across different text mining tasks. Sparse computation using inverted indices is proposed for inference on probabilistic models. This reduces the computational complexity of the common text mining operations according to sparsity, yielding probabilistic models with the scalability of modern search engines.The proposed combination provides sparse generative models: a solution for text mining that is general, effective, and scalable. Extensive experimentation on text classification and ranked retrieval datasets are conducted, showing that the proposed solution matches or outperforms the leading task-specific methods in effectiveness, with a order of magnitude decrease in classification times for Wikipedia article categorization with a million classes. The developed methods were further applied in two 2014 Kaggle data mining prize competitions with over a hundred competing teams, earning first and second places.

show abstract

Section: Expectation Maximizationmentioning

confidence: 99%

Scalable Text Mining with Sparse Generative Models

Puurula

2016

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…During the last decade, a new theory was suggested by neurolinguistics known as dual stream model of speech processing which involves two different streams that works in parallel, one involved in phonological processing and one in articulatory processing (Hickok and Poippil 2007). Based on this approach, Puurula and Compernolla (2010) proposed the idea of dual stream speech recognition by utilizing the complementary features of two methods, dynamic time warping (DTW) and HMM (Wachter et al 2007;Axelrod and Maison 2004). This approach uses the syllables as a modeling unit and log linear interpolation is used to integrate the DTW model scores into the decoding.…”

Section: Dual Stream Approachmentioning

confidence: 99%

Acoustic modeling problem for automatic speech recognition system: advances and refinements (Part II)

Aggarwal

Dave

2011

Int J Speech Technol

View full text Add to dashboard Cite

In automatic speech recognition (ASR) systems, hidden Markov models (HMMs) have been widely used for modeling the temporal speech signal. As discussed in Part I, the conventional acoustic models used for ASR have many drawbacks like weak duration modeling and poor discrimination. This paper (Part II) presents a review on the techniques which have been proposed in literature for the refinements of standard HMM methods to cope with their limitations. Current advancements related to this topic are also outlined. The approaches emphasized in this part of review are connectionist approach, explicit duration modeling, discriminative training and margin based estimation methods. Further, various challenges and performance issues such as environmental variability, tied mixture modeling, and handling of distant speech signals are analyzed along with the directions for future research.

show abstract

Efficient MLP constructive training algorithm using a neuron recruiting approach for isolated word recognition system

Masmoudi

Frikha

Chtourou

et al. 2010

Int J Speech Technol

View full text Add to dashboard Cite

This paper describes an efficient constructive training algorithm using a Multi Layer Perceptron (MLP) neural network dedicated for Isolated Word Recognition (IWR) systems. Incremental training procedure was employed and this approach was based on novel hidden neurons recruiting for a single hidden-layer. During Neural Network (NN) training phase, the number of pronunciation samples extracted from the Training Data (TD) was sequentially increased. Optimal structure of the NN classifier with optimized TD size was obtained using this proposed MLP constructive training algorithm. Isolated word recognition system based on MLP neural network was then constructed and tested for recognizing ten words extracted from TIMIT database. Mel Frequency Cepstral Coefficient (MFCC) feature extraction method was employed including energy, first and second derivative coefficients.A proposed Frame-by-Frame Neural Network (FFNN) classification method was explored and compared with the Conventional Neural Network (CNN) classification approach. Principal Component Analysis (PCA) technique was also investigated in order to reduce both TD size as well as recognition system complexity.Experimental results showed superior performance of the proposed FFNN classifier compared to the CNN counter S. Masmoudi ( ) · M. Frikha · A.B. Hamida Technologie de l'information et électronique médicale,

show abstract

Dual stream speech recognition using articulatory syllable models

Cited by 7 publications

References 32 publications

Scalable Text Mining with Sparse Generative Models

Scalable Text Mining with Sparse Generative Models

Acoustic modeling problem for automatic speech recognition system: advances and refinements (Part II)

Efficient MLP constructive training algorithm using a neuron recruiting approach for isolated word recognition system

Contact Info

Product

Resources

About