Sun Workstation and Swissnet Platform for Speech Recognition and Speaker Veriication over the Telephone ?
نویسندگان
چکیده
منابع مشابه
Securized flexible vocabulary voice messaging system on unix workstation with ISDN connection
This paper considers applications of automatic speech recognition and speaker veri cation techniques in developing e cient Voice Messaging Systems for Integrated Services Digital Network (ISDN) based communication systems. The prototype demonstrator presented was developed in the framework of cooperative project which involves two research institutes: the Signal Processing Laboratory (LTS) of t...
متن کاملSecured Vocal Access to Telephone Servers Third Ieee Workshop on Interactive V Oice Technology for Telecommunications Applications Secured Vocal Access to Telephone Servers Third Ieee Workshop on Interactive V Oice Technology for Telecommunications Applications
A n umber of applications of man-machine interaction over the telephone requires a combination of speech recognition and speaker veriication. This paper describes current w ork carried out at IDIAP in the framework of national and European projects. A generic Interactive V oice Server (IVS) is described by means of a graphical formalism. It includes speech recognition based on speaker independe...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملComparison of text - independent speaker recognition methodson telephone speech with
We compare speaker recognition performance of Vector Quantization (VQ), Gaussian Mixture Modeling (GMM) and the Arithmetic Harmonic Sphericity measure (AHS) in adverse telephone speech conditions. The aim is to address the question: how do multimodal VQ and GMM typically compare to the simpler unimodal AHS for matched and mismatched training and testing environments. We study identiication (clo...
متن کامل