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
The topic of this thesis is to implement efficient decoder for speech recognition training system AS...
Abstract. This chapter addresses issues associated with automatic speech recognition (ASR) over mobi...
The influence of encoding and decoding speech on automatic speech recognition is investigated in thi...
The result of this thesis is a modified speech recognizer developed by the company Phonexia, in whic...
The subject of this thesis is an implementation and optimization of speech recognizer for operating ...
The concept of token passing for speech recognition was introduced over 15 years ago. The most popul...
In a system of speech recognition containing words, the recognition requires the com-parison between...
A three-stage architecture for speech recognition is presented including pre-processing, phoneme rec...
We present a two stage automatic speech recognition architecture suited for applications, such asspo...
The essay presents the basic characteristics of human speech recognition, describes systems for the ...
We propose a model for speech recognition that consists of multiple semi-synchronized recognizers op...
This thesis presents work in the area of automatic speech recognition (ASR). The thesis focuses on m...
The parallel implementation of an isolated word recognizer is described in this paper. Each word is ...
Abstract-For large vocabulary continuous speech recognition, speech decoders treat time sequence wit...
Previously, we proposed a flexible two-layered speech recogniser architecture, called FLaVoR. In the...
The topic of this thesis is to implement efficient decoder for speech recognition training system AS...
Abstract. This chapter addresses issues associated with automatic speech recognition (ASR) over mobi...
The influence of encoding and decoding speech on automatic speech recognition is investigated in thi...
The result of this thesis is a modified speech recognizer developed by the company Phonexia, in whic...
The subject of this thesis is an implementation and optimization of speech recognizer for operating ...
The concept of token passing for speech recognition was introduced over 15 years ago. The most popul...
In a system of speech recognition containing words, the recognition requires the com-parison between...
A three-stage architecture for speech recognition is presented including pre-processing, phoneme rec...
We present a two stage automatic speech recognition architecture suited for applications, such asspo...
The essay presents the basic characteristics of human speech recognition, describes systems for the ...
We propose a model for speech recognition that consists of multiple semi-synchronized recognizers op...
This thesis presents work in the area of automatic speech recognition (ASR). The thesis focuses on m...
The parallel implementation of an isolated word recognizer is described in this paper. Each word is ...
Abstract-For large vocabulary continuous speech recognition, speech decoders treat time sequence wit...
Previously, we proposed a flexible two-layered speech recogniser architecture, called FLaVoR. In the...
The topic of this thesis is to implement efficient decoder for speech recognition training system AS...
Abstract. This chapter addresses issues associated with automatic speech recognition (ASR) over mobi...
The influence of encoding and decoding speech on automatic speech recognition is investigated in thi...
.jpg%3Fwidth%3D300&w=3840&q=75)
Add to ORKG