Note:This thesis introduces an architecture for a generic automatic speech recognition (ASR) system which is easily adapted to specific tasks. It then expands the base system to include a Vector Quantizer (VQ) preprocessor and a speaker adaptation (SA) procedure. The VQ preprocessor reduces the amount of computation which must be done on multivariant gaussian mixtures contained within hidden Markov models (HMMs) in order to achieve a realtime speedup. The SA procedure increases the accuracy of the ASR system when the same speaker uses it for a period of time. Both improvements to the base architecture are then tested and evaluated using the TIMIT test set, an Air Traffic Control task set, and a single speaker test set for speaker adaptation...
Research in Automatic Speech Recognition (ASR) has been very intense in recent years with focus give...
This paper investigates the impact of subspace based techniques for acoustic modeling in automatic s...
Summarization: Several adaptation approaches have been proposed in an effort to improve the speech r...
The performance of the speech recognition systems to translate voice to text is still an issue in la...
This paper constitutes a study of several classical and original methods for a speaker adaptation of...
This article presents the Automatic Speaker Recognition System (ASR System), which successfully reso...
This thesis presents work in the area of automatic speech recognition (ASR). The thesis focuses on m...
Automatic speech recognition (ASR) incorporates knowledge and research in linguistics, computer scie...
Texte intégral accessible uniquement aux membres de l'Université de LorraineOne way to improve perfo...
Les trois sources principalement utilisées en reconnaissance vocale automatique (Automatic Speech Re...
State-of-the-art automatic speech recognition (ASR) systems are very complex, combining mul-tiple te...
Automatic speech recognition (ASR) is a very demanding computing task. Much research has been done i...
As a result of advancement in deep learning and neural network technology, end-to-end models have be...
This paper shows the results achieved by the Maxi-mum A Posteriori (MAP) speaker adaptation method i...
This work provide mathematical insight to Automatic Speech Recognition (ASR) system’s algorithm such...
Research in Automatic Speech Recognition (ASR) has been very intense in recent years with focus give...
This paper investigates the impact of subspace based techniques for acoustic modeling in automatic s...
Summarization: Several adaptation approaches have been proposed in an effort to improve the speech r...
The performance of the speech recognition systems to translate voice to text is still an issue in la...
This paper constitutes a study of several classical and original methods for a speaker adaptation of...
This article presents the Automatic Speaker Recognition System (ASR System), which successfully reso...
This thesis presents work in the area of automatic speech recognition (ASR). The thesis focuses on m...
Automatic speech recognition (ASR) incorporates knowledge and research in linguistics, computer scie...
Texte intégral accessible uniquement aux membres de l'Université de LorraineOne way to improve perfo...
Les trois sources principalement utilisées en reconnaissance vocale automatique (Automatic Speech Re...
State-of-the-art automatic speech recognition (ASR) systems are very complex, combining mul-tiple te...
Automatic speech recognition (ASR) is a very demanding computing task. Much research has been done i...
As a result of advancement in deep learning and neural network technology, end-to-end models have be...
This paper shows the results achieved by the Maxi-mum A Posteriori (MAP) speaker adaptation method i...
This work provide mathematical insight to Automatic Speech Recognition (ASR) system’s algorithm such...
Research in Automatic Speech Recognition (ASR) has been very intense in recent years with focus give...
This paper investigates the impact of subspace based techniques for acoustic modeling in automatic s...
Summarization: Several adaptation approaches have been proposed in an effort to improve the speech r...