際際滷shows by User: gtiwari / http://www.slideshare.net/images/logo.gif 際際滷shows by User: gtiwari / Sat, 18 Jun 2011 03:03:44 GMT 際際滷Share feed for 際際滷shows by User: gtiwari Text Prompted Remote Speaker Authentication : Joint Speech and Speaker Recognition/Verification System Mid-term Project Presentation /slideshow/text-prompted-remote-speaker-authentication-joint-speech-and-speaker-recognitionverification-system-midterm-project-presentation/8343665 mid-termpresspeakerverificationforremoteauthentication-110618030349-phpapp01
Joint Speech and Speaker Recognition using Hidden Markov Model/Vector Quantization for speaker independent Speech Recognition and Gaussian Mixture Model for speech independent speaker recognition- used MFCC (Mel-Frequency Cepstral Coefficient) for Feature Extraction (delta,delta delta and energy - 39 coefficients). Developed in JAVA with client/server Architecture, web interface developed in Adobe Flex. This project was done at TU, IOE - Pulchowk Campus, Nepal. For more details visit http://ganeshtiwaridotcomdotnp.blogspot.com ABSTRACT OF PROJECT>>> Biometric is physical characteristic unique to each individual. It has a very useful application in authentication and access control. The designed system is a text-prompted version of voice biometric which incorporates text-independent speaker verification and speaker-independent speech verification system implemented independently. The foundation for this joint system is that the speech signal conveys both the speech content and speaker identity. Such systems are more-secure from playback attack, since the word to speak during authentication is not previously set. During the course of the project various digital signal processing and pattern classification algorithms were studied. Short time spectral analysis was performed to obtain MFCC, energy and their deltas as feature. Feature extraction module is same for both systems. Speaker modeling was done by GMM and Left to Right Discrete HMM with VQ was used for isolated word modeling. And results of both systems were combined to authenticate the user. The speech model for each word was pre-trained by using utterance of 45 English words. The speaker model was trained by utterance of about 2 minutes each by 15 speakers. While uttering the individual words, the recognition rate of the speech recognition system is 92 % and speaker recognition system is 66%. For longer duration of utterance (>5sec) the recognition rate of speaker recognition system improves to 78%. ]]>
Joint Speech and Speaker Recognition using Hidden Markov Model/Vector Quantization for speaker independent Speech Recognition and Gaussian Mixture Model for speech independent speaker recognition- used MFCC (Mel-Frequency Cepstral Coefficient) for Feature Extraction (delta,delta delta and energy - 39 coefficients). Developed in JAVA with client/server Architecture, web interface developed in Adobe Flex. This project was done at TU, IOE - Pulchowk Campus, Nepal. For more details visit http://ganeshtiwaridotcomdotnp.blogspot.com ABSTRACT OF PROJECT>>> Biometric is physical characteristic unique to each individual. It has a very useful application in authentication and access control. The designed system is a text-prompted version of voice biometric which incorporates text-independent speaker verification and speaker-independent speech verification system implemented independently. The foundation for this joint system is that the speech signal conveys both the speech content and speaker identity. Such systems are more-secure from playback attack, since the word to speak during authentication is not previously set. During the course of the project various digital signal processing and pattern classification algorithms were studied. Short time spectral analysis was performed to obtain MFCC, energy and their deltas as feature. Feature extraction module is same for both systems. Speaker modeling was done by GMM and Left to Right Discrete HMM with VQ was used for isolated word modeling. And results of both systems were combined to authenticate the user. The speech model for each word was pre-trained by using utterance of 45 English words. The speaker model was trained by utterance of about 2 minutes each by 15 speakers. While uttering the individual words, the recognition rate of the speech recognition system is 92 % and speaker recognition system is 66%. For longer duration of utterance (>5sec) the recognition rate of speaker recognition system improves to 78%. ]]> Sat, 18 Jun 2011 03:03:44 GMT /slideshow/text-prompted-remote-speaker-authentication-joint-speech-and-speaker-recognitionverification-system-midterm-project-presentation/8343665 gtiwari@slideshare.net(gtiwari) Text Prompted Remote Speaker Authentication : Joint Speech and Speaker Recognition/Verification System Mid-term Project Presentation gtiwari Joint Speech and Speaker Recognition using Hidden Markov Model/Vector Quantization for speaker independent Speech Recognition and Gaussian Mixture Model for speech independent speaker recognition- used MFCC (Mel-Frequency Cepstral Coefficient) for Feature Extraction (delta,delta delta and energy - 39 coefficients). Developed in JAVA with client/server Architecture, web interface developed in Adobe Flex. This project was done at TU, IOE - Pulchowk Campus, Nepal. For more details visit http://ganeshtiwaridotcomdotnp.blogspot.com ABSTRACT OF PROJECT>>> Biometric is physical characteristic unique to each individual. It has a very useful application in authentication and access control. The designed system is a text-prompted version of voice biometric which incorporates text-independent speaker verification and speaker-independent speech verification system implemented independently. The foundation for this joint system is that the speech signal conveys both the speech content and speaker identity. Such systems are more-secure from playback attack, since the word to speak during authentication is not previously set. During the course of the project various digital signal processing and pattern classification algorithms were studied. Short time spectral analysis was performed to obtain MFCC, energy and their deltas as feature. Feature extraction module is same for both systems. Speaker modeling was done by GMM and Left to Right Discrete HMM with VQ was used for isolated word modeling. And results of both systems were combined to authenticate the user. The speech model for each word was pre-trained by using utterance of 45 English words. The speaker model was trained by utterance of about 2 minutes each by 15 speakers. While uttering the individual words, the recognition rate of the speech recognition system is 92 % and speaker recognition system is 66%. For longer duration of utterance (>5sec) the recognition rate of speaker recognition system improves to 78%. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/mid-termpresspeakerverificationforremoteauthentication-110618030349-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Joint Speech and Speaker Recognition using Hidden Markov Model/Vector Quantization for speaker independent Speech Recognition and Gaussian Mixture Model for speech independent speaker recognition- used MFCC (Mel-Frequency Cepstral Coefficient) for Feature Extraction (delta,delta delta and energy - 39 coefficients). Developed in JAVA with client/server Architecture, web interface developed in Adobe Flex. This project was done at TU, IOE - Pulchowk Campus, Nepal. For more details visit http://ganeshtiwaridotcomdotnp.blogspot.com ABSTRACT OF PROJECT&gt;&gt;&gt; Biometric is physical characteristic unique to each individual. It has a very useful application in authentication and access control. The designed system is a text-prompted version of voice biometric which incorporates text-independent speaker verification and speaker-independent speech verification system implemented independently. The foundation for this joint system is that the speech signal conveys both the speech content and speaker identity. Such systems are more-secure from playback attack, since the word to speak during authentication is not previously set. During the course of the project various digital signal processing and pattern classification algorithms were studied. Short time spectral analysis was performed to obtain MFCC, energy and their deltas as feature. Feature extraction module is same for both systems. Speaker modeling was done by GMM and Left to Right Discrete HMM with VQ was used for isolated word modeling. And results of both systems were combined to authenticate the user. The speech model for each word was pre-trained by using utterance of 45 English words. The speaker model was trained by utterance of about 2 minutes each by 15 speakers. While uttering the individual words, the recognition rate of the speech recognition system is 92 % and speaker recognition system is 66%. For longer duration of utterance (&gt;5sec) the recognition rate of speaker recognition system improves to 78%.
Text Prompted Remote Speaker Authentication : Joint Speech and Speaker Recognition/Verification System Mid-term Project Presentation from gt_ebuddy
]]> 3117 11 https://cdn.slidesharecdn.com/ss_thumbnails/mid-termpresspeakerverificationforremoteauthentication-110618030349-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Text Prompted Remote Speaker Authentication : Joint Speech and Speaker Recognition/Verification System Final Presentation 際際滷 /slideshow/text-prompted-remote-speaker-authentication-joint-speech-and-speaker-recognitionverification-system-final-presentation-slide/8343556 finalpresspeakerverificationforremoteauthentication-110618025008-phpapp01
Joint Speech and Speaker Recognition using Hidden Markov Model/Vector Quantization for speaker independent Speech Recognition and Gaussian Mixture Model for speech independent speaker recognition- used MFCC (Mel-Frequency Cepstral Coefficient) for Feature Extraction (delta,delta delta and energy - 39 coefficients). Developed in JAVA with client/server Architecture, web interface developed in Adobe Flex. This project was done at TU, IOE - Pulchowk Campus, Nepal. For more details visit http://ganeshtiwaridotcomdotnp.blogspot.com ABSTRACT OF PROJECT>>> Biometric is physical characteristic unique to each individual. It has a very useful application in authentication and access control. The designed system is a text-prompted version of voice biometric which incorporates text-independent speaker verification and speaker-independent speech verification system implemented independently. The foundation for this joint system is that the speech signal conveys both the speech content and speaker identity. Such systems are more-secure from playback attack, since the word to speak during authentication is not previously set. During the course of the project various digital signal processing and pattern classification algorithms were studied. Short time spectral analysis was performed to obtain MFCC, energy and their deltas as feature. Feature extraction module is same for both systems. Speaker modeling was done by GMM and Left to Right Discrete HMM with VQ was used for isolated word modeling. And results of both systems were combined to authenticate the user. The speech model for each word was pre-trained by using utterance of 45 English words. The speaker model was trained by utterance of about 2 minutes each by 15 speakers. While uttering the individual words, the recognition rate of the speech recognition system is 92 % and speaker recognition system is 66%. For longer duration of utterance (>5sec) the recognition rate of speaker recognition system improves to 78%. ]]>
Joint Speech and Speaker Recognition using Hidden Markov Model/Vector Quantization for speaker independent Speech Recognition and Gaussian Mixture Model for speech independent speaker recognition- used MFCC (Mel-Frequency Cepstral Coefficient) for Feature Extraction (delta,delta delta and energy - 39 coefficients). Developed in JAVA with client/server Architecture, web interface developed in Adobe Flex. This project was done at TU, IOE - Pulchowk Campus, Nepal. For more details visit http://ganeshtiwaridotcomdotnp.blogspot.com ABSTRACT OF PROJECT>>> Biometric is physical characteristic unique to each individual. It has a very useful application in authentication and access control. The designed system is a text-prompted version of voice biometric which incorporates text-independent speaker verification and speaker-independent speech verification system implemented independently. The foundation for this joint system is that the speech signal conveys both the speech content and speaker identity. Such systems are more-secure from playback attack, since the word to speak during authentication is not previously set. During the course of the project various digital signal processing and pattern classification algorithms were studied. Short time spectral analysis was performed to obtain MFCC, energy and their deltas as feature. Feature extraction module is same for both systems. Speaker modeling was done by GMM and Left to Right Discrete HMM with VQ was used for isolated word modeling. And results of both systems were combined to authenticate the user. The speech model for each word was pre-trained by using utterance of 45 English words. The speaker model was trained by utterance of about 2 minutes each by 15 speakers. While uttering the individual words, the recognition rate of the speech recognition system is 92 % and speaker recognition system is 66%. For longer duration of utterance (>5sec) the recognition rate of speaker recognition system improves to 78%. ]]> Sat, 18 Jun 2011 02:50:02 GMT /slideshow/text-prompted-remote-speaker-authentication-joint-speech-and-speaker-recognitionverification-system-final-presentation-slide/8343556 gtiwari@slideshare.net(gtiwari) Text Prompted Remote Speaker Authentication : Joint Speech and Speaker Recognition/Verification System Final Presentation 際際滷 gtiwari Joint Speech and Speaker Recognition using Hidden Markov Model/Vector Quantization for speaker independent Speech Recognition and Gaussian Mixture Model for speech independent speaker recognition- used MFCC (Mel-Frequency Cepstral Coefficient) for Feature Extraction (delta,delta delta and energy - 39 coefficients). Developed in JAVA with client/server Architecture, web interface developed in Adobe Flex. This project was done at TU, IOE - Pulchowk Campus, Nepal. For more details visit http://ganeshtiwaridotcomdotnp.blogspot.com ABSTRACT OF PROJECT>>> Biometric is physical characteristic unique to each individual. It has a very useful application in authentication and access control. The designed system is a text-prompted version of voice biometric which incorporates text-independent speaker verification and speaker-independent speech verification system implemented independently. The foundation for this joint system is that the speech signal conveys both the speech content and speaker identity. Such systems are more-secure from playback attack, since the word to speak during authentication is not previously set. During the course of the project various digital signal processing and pattern classification algorithms were studied. Short time spectral analysis was performed to obtain MFCC, energy and their deltas as feature. Feature extraction module is same for both systems. Speaker modeling was done by GMM and Left to Right Discrete HMM with VQ was used for isolated word modeling. And results of both systems were combined to authenticate the user. The speech model for each word was pre-trained by using utterance of 45 English words. The speaker model was trained by utterance of about 2 minutes each by 15 speakers. While uttering the individual words, the recognition rate of the speech recognition system is 92 % and speaker recognition system is 66%. For longer duration of utterance (>5sec) the recognition rate of speaker recognition system improves to 78%. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/finalpresspeakerverificationforremoteauthentication-110618025008-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Joint Speech and Speaker Recognition using Hidden Markov Model/Vector Quantization for speaker independent Speech Recognition and Gaussian Mixture Model for speech independent speaker recognition- used MFCC (Mel-Frequency Cepstral Coefficient) for Feature Extraction (delta,delta delta and energy - 39 coefficients). Developed in JAVA with client/server Architecture, web interface developed in Adobe Flex. This project was done at TU, IOE - Pulchowk Campus, Nepal. For more details visit http://ganeshtiwaridotcomdotnp.blogspot.com ABSTRACT OF PROJECT&gt;&gt;&gt; Biometric is physical characteristic unique to each individual. It has a very useful application in authentication and access control. The designed system is a text-prompted version of voice biometric which incorporates text-independent speaker verification and speaker-independent speech verification system implemented independently. The foundation for this joint system is that the speech signal conveys both the speech content and speaker identity. Such systems are more-secure from playback attack, since the word to speak during authentication is not previously set. During the course of the project various digital signal processing and pattern classification algorithms were studied. Short time spectral analysis was performed to obtain MFCC, energy and their deltas as feature. Feature extraction module is same for both systems. Speaker modeling was done by GMM and Left to Right Discrete HMM with VQ was used for isolated word modeling. And results of both systems were combined to authenticate the user. The speech model for each word was pre-trained by using utterance of 45 English words. The speaker model was trained by utterance of about 2 minutes each by 15 speakers. While uttering the individual words, the recognition rate of the speech recognition system is 92 % and speaker recognition system is 66%. For longer duration of utterance (&gt;5sec) the recognition rate of speaker recognition system improves to 78%.
Text Prompted Remote Speaker Authentication : Joint Speech and Speaker Recognition/Verification System Final Presentation 際際滷 from gt_ebuddy
]]> 2536 10 https://cdn.slidesharecdn.com/ss_thumbnails/finalpresspeakerverificationforremoteauthentication-110618025008-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-gtiwari-48x48.jpg?cb=1577675979 Interested in 01. IOE, Pulchowk Campus ganeshtiwaridotcomdotnp.blogspot.com https://cdn.slidesharecdn.com/ss_thumbnails/mid-termpresspeakerverificationforremoteauthentication-110618030349-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/text-prompted-remote-speaker-authentication-joint-speech-and-speaker-recognitionverification-system-midterm-project-presentation/8343665 Text Prompted Remote S... https://cdn.slidesharecdn.com/ss_thumbnails/finalpresspeakerverificationforremoteauthentication-110618025008-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/text-prompted-remote-speaker-authentication-joint-speech-and-speaker-recognitionverification-system-final-presentation-slide/8343556 Text Prompted Remote S...