Downloads: 108 | Views: 157
M.Tech / M.E / PhD Thesis | Electronics & Communication Engineering | India | Volume 4 Issue 5, May 2015
HMM Based Distributed Speech Processing Distributed Speech Recognition
Abstract: Distributed speech recognition (DSR) is a concept which performs speech recognition over a network. It mainly focuses to assist physically challenged and visually impaired individuals to use internet services with as ease as that of others. DSR adopts the client/server methodology for implementing recognition process over internet. In combination with the HMM based recognition systems, distributed speech recognition (DSR) can deliver a highly flexible and scalable system of speech recognition. An example based on DSR can be thought of as in a meeting or discussion room, the meeting notes can be directly taken down in our handset and can be shared with all the stakeholders immediately after the meeting. The performance of speech recognition systems receiving speech that has been transmitted over mobile channels can be significantly degraded when compared to using an unmodified signal. The degradations are as a result of both the low bit rate speech coding and channel transmission errors. A Distributed Speech Recognition (DSR) system overcomes these problems by eliminating the speech channel and instead using an error protected data channel to send a parameterized representation of the speech, which is suitable for recognition. The processing is distributed between the terminal and the network. The terminal performs the feature parameter extraction, or the front-end of the speech recognition system. These features are transmitted over a data channel to a remote back-end recognizer. The back-end server recognizes speech from the received stream of parameter vectors, uses phoneme based HMM models and recognizes the speech.
Keywords: Distributed Speech Processing, Speech Recognition, Client-Server model, HMM, Acoustic Model
Edition: Volume 4 Issue 5, May 2015,
Pages: 2764 - 2766