The QUT NIST 2004 Speaker Verification System: A fused acoustic and high-level approach
نویسندگان
چکیده
The trend towards including both acoustic and high level speech features in speaker recognition systems is addressed with the presentation of the speaker verification system developed by QUT for the NIST 2004 Speaker Recognition Evaluation. The system presented is a fusion of five subsystems including acoustic, lexical, phonetic, prosodic and durational speech features and focuses on utilising the high level feature sets in reduced training set conditions. The performance of the system on the development data resources available in the NIST SRE are presented to demonstrate the effectiveness of the fused system approach.
منابع مشابه
Qut Speaker Identity Verification System for Evalita
This document outlines the system submitted by the Speech and Audio Research Laboratory at the Queensland University of Technology (QUT) for the Speaker Identity Verification: Application task of EVALITA 2009. This competitive submission consisted of a score-level fusion of three component systems; a joint-factor analysis GMM system and two SVM systems using GLDS and GMM supervector kernels. De...
متن کاملSpeaker detection using acoustic event sequences
Novel approaches using high level features have recently shown up in the speaker recognition field. They basically consist in modeling speakers using linguistic features such as words, phonemes, idiolects. The benefit of these features was demonstrated in NIST campaigns. Their main disadvantage is their need of a huge amount of data to be efficient. The purpose of this study is to generalize th...
متن کاملFusing acoustic, phonetic and data-driven systems for text-independent speaker verification
This paper describes our recent efforts in exploring datadriven high-level features and their combination with low-level spectral features for speaker verification. In particular, we compare the phonetic and data-driven approaches and study their complementarity with short-term acoustic approach. Our objective is to show that data-driven units automatically acquired from the speech data, can be...
متن کاملExploiting High-Level Information Provided by ALISP in Speaker Recognition
The best performing systems in the area of automatic speaker recognition have focused on using short-term, low-level acoustic information, such as sepstral features. Recently, various works have demonstrated that high-level features convey more speaker information and can be added to the low-level features in order to increase the robustness of the system. This paper describes a text-independen...
متن کاملDuration and pronunciation conditioned lexical modeling for speaker verification
We propose a method to improve speaker recognition lexical model performance using acoustic-prosodic information. More specifically, the lexical model is trained using durationand pronunciation-conditioned word N-grams, simultaneously modeling lexical information along with their acoustic and prosodic characteristics. Support vector machines are used for modeling and scoring, with N-gram freque...
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 2004