Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Incorporating Knowledge Sources into Statistical Speech Recognition offers solutions for enhancing the robustness of a statistical automatic speech recognition (ASR) system by incorporating various additional knowledge sources while keeping the training and recognition effort feasible. The authors provide an efficient general framework for incorporating knowledge sources into state-of-the-art statistical ASR systems. This framework, which is called GFIKS (graphical framework to incorporate additional knowledge sources), was designed by utilizing the concept of the Bayesian network (BN) framework. This framework allows probabilistic relationships among different information sources to be learned, various kinds of knowledge sources to be incorporated, and a probabilistic function of the model to be formulated. Incorporating Knowledge Sources into Statistical Speech Recognition demonstrates how the statistical speech recognition system may incorporate additional information sources by utilizing GFIKS at different levels of ASR. The incorporation of various knowledge sources, including background noises, accent, gender and wide phonetic knowledge information, in modeling is discussed theoretically and analyzed experimentally.

Automatic speech recognition. --- Pattern recognition systems. --- Signal processing. --- Speech processing systems. --- Electrical Engineering --- Electrical & Computer Engineering --- Engineering & Applied Sciences --- Automatic speech recognition --- Electrical engineering. --- Statistical methods. --- Electric engineering --- Mechanical speech recognizer --- Speech recognition, Automatic --- Acoustics. --- Telecommunication. --- Computer Communication Networks. --- Computer engineering. --- Signal, Image and Speech Processing. --- Communications Engineering, Networks. --- Electrical Engineering. --- Computers --- Electric communication --- Mass communication --- Telecom --- Telecommunication industry --- Telecommunications --- Communication --- Information theory --- Telecommuting --- Design and construction --- Engineering --- Pattern recognition systems --- Perceptrons --- Speech, Intelligibility of --- Speech perception --- Speech processing systems --- Image processing. --- Computer communication systems. --- Computational linguistics --- Electronic systems --- Modulation theory --- Oral communication --- Speech --- Telecommunication --- Singing voice synthesizers --- Pictorial data processing --- Picture processing --- Processing, Image --- Imaging systems --- Optical data processing --- Communication systems, Computer --- Computer communication systems --- Data networks, Computer --- ECNs (Electronic communication networks) --- Electronic communication networks --- Networks, Computer --- Teleprocessing networks --- Data transmission systems --- Digital communications --- Information networks --- Cyberinfrastructure --- Electronic data processing --- Network computers --- Processing, Signal --- Information measurement --- Signal theory (Telecommunication) --- Distributed processing

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Incorporating Knowledge Sources into Statistical Speech Recognition offers solutions for enhancing the robustness of a statistical automatic speech recognition (ASR) system by incorporating various additional knowledge sources while keeping the training and recognition effort feasible. The authors provide an efficient general framework for incorporating knowledge sources into state-of-the-art statistical ASR systems. This framework, which is called GFIKS (graphical framework to incorporate additional knowledge sources), was designed by utilizing the concept of the Bayesian network (BN) framework. This framework allows probabilistic relationships among different information sources to be learned, various kinds of knowledge sources to be incorporated, and a probabilistic function of the model to be formulated. Incorporating Knowledge Sources into Statistical Speech Recognition demonstrates how the statistical speech recognition system may incorporate additional information sources by utilizing GFIKS at different levels of ASR. The incorporation of various knowledge sources, including background noises, accent, gender and wide phonetic knowledge information, in modeling is discussed theoretically and analyzed experimentally.

Vibrations --- Electrical engineering --- Applied physical engineering --- Mass communications --- Computer architecture. Operating systems --- Computer. Automation --- geluidsleer --- akoestiek --- beeldverwerking --- spraaktechnologie --- computernetwerken --- elektrotechniek --- communicatietechnologie --- signaalverwerking