|
|
Parallel Training of Neural Networks for Speech Recognition
Veselý, Karel ; Fousek, Petr (referee) ; Burget, Lukáš (advisor)
This thesis deals with different parallelizations of training procedure for artificial neural networks. The networks are trained as phoneme-state acoustic descriptors for speech recognition. Two effective parallelization strategies were implemented and compared. The first strategy is data parallelization, where the training is split into several POSIX threads. The second strategy is node parallelization, which uses CUDA framework for general purpose computing on modern graphic cards. The first strategy showed a 4x speed-up, while using the second strategy we observed nearly 10x speed-up. The Stochastic Gradient Descent algorithm with error backpropagation was used for the training. After a short introduction, the second chapter of this thesis shows the motivation and introduces the neural networks into the context of speech recognition. The third chapter is theoretical, the anatomy of a neural network and the used training method are discussed. The following chapters are focused on the design and implementation of the project, while the phases of the iterative development are described. The last extensive chapter describes the setup of the testing system and reports the experimental results. Finally, the obtained results are concluded and the possible extensions of the project are proposed.
|
|
|
Unsupervised Adaptation of Speech Recognizer
Švec, Ján ; Karafiát, Martin (referee) ; Schwarz, Petr (advisor)
The goal of this thesis is to design and test techniques for unsupervised adaptation of speech recognizers on some audio data without any textual transcripts. A training set is prepared at first, and a baseline speech recognition system is trained. This sistem is used to transcribe some unseen data. We will experiment with an adaptation data selection process based on some speech transcript quality measurement. The system is re-trained on this new set than, and the accuracy is evaluated. Then we experiment with the amount of adaptation data.
|
|
|
Gaze-Based Keyboard
Sznapka, Jakub ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The goal of this bachelor's thesis is to create a tool for gaze typing. It deals with gaze tracking and evalution issues. It contains a description of the Swype method which is used for typing on touch screen devices. Then follows the analysis of different ways which could be used to model the language used by model. The main part is dedicated to design of the gaze typing tool and implementation using the Kaldi toolkit.
|
|
|
Recurrent Neural Networks for Speech Recognition
Nováčik, Tomáš ; Karafiát, Martin (referee) ; Veselý, Karel (advisor)
This master thesis deals with the implementation of various types of recurrent neural networks via programming language lua using torch library. It focuses on finding optimal strategy for training recurrent neural networks and also tries to minimize the duration of the training. Furthermore various types of regularization techniques are investigated and implemented into the recurrent neural network architecture. Implemented recurrent neural networks are compared on the speech recognition task using AMI dataset, where they model the acustic information. Their performance is also compared to standard feedforward neural network. Best results are achieved using BLSTM architecture. The recurrent neural network are also trained via CTC objective function on the TIMIT dataset. Best result is again achieved using BLSTM architecture.
|
|
|
Speech recognition using Sphinx-4
Kryške, Lukáš ; Uher, Václav (referee) ; Burget, Radim (advisor)
This diploma thesis is aimed to find an effective method for continuous speech recognition. To be more accurate, it uses speech-to-text recognition for a keyword spotting discipline. This solution is able to be applicable for phone calls analysis or for a similar application. Most of the diploma thesis describes and implements speech recognition framework Sphinx-4 which uses Hidden Markov models (HMM) to define a language acoustic models. It is explained how these models can be trained for a new language or for a new language dialect. Finally there is in detail described how to implement the keyword spotting in the Java language.
|
|
|
Topic Identification from Spoken TED-Talks
Vašš, Adam ; Ondel, Lucas Antoine Francois (referee) ; Kesiraju, Santosh (advisor)
Táto práca sa zaoberá problémom spracovania prirodzeného jazyka a následnej klasifikácie. Použité systémy boli modelované na TED-LIUM korpuse. Systém automatického spracovania jazyka bol modelovaný s použitím sady nástrojov Kaldi. Vo výsledku bol dosiahnutý WER s hodnotou 16.6%. Problém klasifikácie textu bol adresovaný s pomocou metód na lineárnu klasifikáciu, konkrétne Multinomial Naive Bayes a Linear Support Vector Machines, kde druhá technika dosiahla vyššiu presnosť klasifikácie.
|
|
|
Dynamic Decoder for Speech Recognition
Veselý, Michal ; Glembek, Ondřej (referee) ; Schwarz, Petr (advisor)
The result of this work is a fully working and significantly optimized implementation of a dynamic decoder. This decoder is based on dynamic recognition network generation and decoding by a modified version of the Token Passing algorithm. The implemented solution provides very similar results to the original static decoder from BSCORE (API of Phonexia company). Compared to BSCORE this implementation offers significant reduction of memory usage. This makes use of more complex language models possible. It also facilitates integration the speech recognition to some mobile devices or dynamic adding of new words to the system.
|
|
|
Topic Identification from Spoken TED-Talks
Vašš, Adam ; Ondel, Lucas Antoine Francois (referee) ; Kesiraju, Santosh (advisor)
Táto práca sa zaoberá problémom spracovania prirodzeného jazyka a následnej klasifikácie. Použité systémy boli modelované na TED-LIUM korpuse. Systém automatického spracovania jazyka bol modelovaný s použitím sady nástrojov Kaldi. Vo výsledku bol dosiahnutý WER s hodnotou 16.6\%. Problém klasifikácie textu bol adresovaný s pomocou metód na lineárnu klasifikáciu, konkrétne Multinomial Naive Bayes a Linear Support Vector Machines, kde druhá technika dosiahla vyššiu presnosť klasifikácie.
|
|
|
Topic Identification from Spoken TED-Talks
Vašš, Adam ; Ondel, Lucas Antoine Francois (referee) ; Kesiraju, Santosh (advisor)
Táto práca sa zaoberá problémom spracovania prirodzeného jazyka a následnej klasifikácie. Použité systémy boli modelované na TED-LIUM korpuse. Systém automatického spracovania jazyka bol modelovaný s použitím sady nástrojov Kaldi. Vo výsledku bol dosiahnutý WER s hodnotou 16.6%. Problém klasifikácie textu bol adresovaný s pomocou metód na lineárnu klasifikáciu, konkrétne Multinomial Naive Bayes a Linear Support Vector Machines, kde druhá technika dosiahla vyššiu presnosť klasifikácie.
|
|
|
Topic Identification from Spoken TED-Talks
Vašš, Adam ; Ondel, Lucas Antoine Francois (referee) ; Kesiraju, Santosh (advisor)
Táto práca sa zaoberá problémom spracovania prirodzeného jazyka a následnej klasifikácie. Použité systémy boli modelované na TED-LIUM korpuse. Systém automatického spracovania jazyka bol modelovaný s použitím sady nástrojov Kaldi. Vo výsledku bol dosiahnutý WER s hodnotou 16.6\%. Problém klasifikácie textu bol adresovaný s pomocou metód na lineárnu klasifikáciu, konkrétne Multinomial Naive Bayes a Linear Support Vector Machines, kde druhá technika dosiahla vyššiu presnosť klasifikácie.
|
guest ::
