Text-d Dependent Speaker Verification System An Experiment Using Hidden Markov Model (hmm)

As the popularity of biometrics increase as a means of securing data and locations, thernarea of speaker recognition is emerging as an important fie ld of current research. Sincernspeech is our most natural means of communicate ion having enough identifyingrncharacteristics, speaker recognition has become a desirable method of determining arnperson’s identity. This thesis examines the field of speaker verification in which arnspeaker' s identity claim is ,'verified from a sample of speech, The experiment mainlyrnfocuses on HMM-based text-dependent speaker verification system experimented byrnusing a word from the Amharic language. In the course of building the verificationrnsystem, the popular Hidden Marcov Model Toolkit (HTK) is used. For each client, six different utterances are taken in two sessions and phone-basedrnHMM is developed, Speech of each client is collected at different sessions for testingrnpurpose. Away from the client set a speech (of the word used in the experiment) isrncollected for testing purpose, The results obtained are promising in that. only two false acceptances out of the ninetyrnnine false claims, and one false reject out of the ninety true claims, errors arernc01l1mitted, giving a 0,02 FAR and 0.01 FRR. The details of the research and findingsrnarc discussed in the paper. Conclusions of the findings as well as future directions arernrecommended

Get Full Work

Report copyright infringement or plagiarism