General phrase speaker verification using sub-word background models and likelihood-ratio scoring
نویسندگان
چکیده
We present a design and study the performance of a text-dependent speaker veri cation system using general phrase passwords. The text of the password utterance and its phone transcription are assumed to be available. The problems that are addressed include the appropriate choice of units for building target speaker models and the choice of background models for likelihoodratio scoring.
منابع مشابه
Incorporating pass-phrase dependent background models for text-dependent speaker verification
In this paper, we propose a pass-phrase dependent background model (PBM) for text dependent (TD) speaker verification (SV) to integrate pass-phrase identification process (without an additional separate identification system) in the conventional TD-SV system, where a PBM is derived from a text-independent background model through adaptation using the utterances of a particular pass-phrase. Duri...
متن کاملHigh-level speaker verification via articulatory-feature based sequence kernels and SVM
Articulatory-feature based pronunciation models (AFCPMs) are capable of capturing the pronunciation variations among different speakers and are good for high-level speaker recognition. However, the likelihood-ratio scoring method of AFPCMs is based on a decision boundary created by training the target speaker model and universal background model (UBM) separately. Therefore, the method does not ...
متن کاملSub-word Speaker Verification Using Data Fusion Methods
peaker verification is a rapidly maturing technology that is beoming available for commercial applications. In this paper, we westigate the application of data fusion methods to sub-word imlementations of speaker verification. At a sub-word level, we utize the diversity of the information provided by the neural tree etwork and Gaussian mixture model to provide a more robust ub-word model. The p...
متن کاملSpeaker Verification using Support Vector
pretations, conclusions, and recommendations are those of the authors and are not necessarily endorsed by the United States Government. Abstract High-level features such as word usage, pronunciation, phonotactics, prosody, etc., have seen a resurgence for automatic speaker recognition over the last few years. With the availability of many conversations per speaker in current corpora, high-level...
متن کاملUtterance Verification Using State-Level Log-Likelihood Ratio with Frame and State Selection
This paper suggests utterance verification system using state-level log-likelihood ratio with frame and state selection. We use hidden Markov models for speech recognition and utterance verification as acoustic models and anti-phone models. The hidden Markov models have three states and each state represents different characteristics of a phone. Thus we propose an algorithm to compute state-lev...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1996