NAP, WCCN, a New Linear Kernel, and Keyword Weighting for the HMM Supervector Speaker Recognition System
نویسنده
چکیده
We demonstrate the application of Nuisance Attribute Projection (NAP), Within-Class Covariance Normalization (WCCN), a new standard kernel, and keyword weighting for the keywordbased HMM supervector speaker recognition system. On our development set (SRE04 8-side training), we achieve 22.6% and 16.2% EER improvements using NAP and WCCN respectively, a 19.5% EER improvement using NAP and WCCN jointly, and a 8.6% DCF improvement using keyword weighting. We also demonstrate the lack of effectiveness of gender separation in our NAP training, and counter-intuitive results using various modifications to the NAP technique. On our non-development set (SRE05 8-side training), we achieve a 5.3% EER and 18.6% DCF improvement using NAP and keyword-weighting, and a 13.7% EER and 12.3% DCF improvement using WCCN.
منابع مشابه
Linear and non linear kernel GMM supervector machines for speaker verification
This paper presents a comparison between Support Vector Machines (SVM) speaker verification systems based on linear and non linear kernels defined in GMM supervector space. We describe how these kernel functions are related and we show how the nuisance attribute projection (NAP) technique can be used with both of these kernels to deal with the session variability problem. We demonstrate the imp...
متن کاملComparisons of recent speaker recognition approaches based on word-conditioning
We examine the effectiveness of various speaker recognition approaches based on word-conditioning. Subsets of 62 keywords (used for word-conditioning) are examined for their individual and combined effectiveness for a keyword HMM approach, a supervector keyword HMM approach, a keyword phone Ngrams approach, and a keyword phone HMM approach. Our results demonstrate the effectiveness of acoustic ...
متن کاملText-Independent Speaker Verification via State Alignment
To model the speech utterance at a finer granularity, this paper presents a novel state-alignment based supervector modeling method for text-independent speaker verification, which takes advantage of state-alignment method used in hidden Markov model (HMM) based acoustic modeling in speech recognition. By this way, the proposed modeling method can convert a text-independent speaker verification...
متن کاملKernel combination for SVM speaker verification
We present a new approach to construct kernels used on support vector machines for speaker verification. The idea is to learn new kernels by taking linear combination of many kernels such as the Generalized Linear Discriminant Sequence kernels (GLDS) and Gaussian Mixture Models (GMM) supervector kernels. In this new linear kernel combination, the weights are speaker dependent rather than univer...
متن کاملSupport vector machines based text dependent speaker verification using HMM supervectors
Conventional subword based hidden Markov models (HMMs) have proven to be an effective approach for text-dependent speaker verification. The standard training method works by modeling the MAP adapted means of subword HMMs. In this paper, we propose the use of HMM supervectors from the speaker models as features in support vector machines (SVMs) classifier. An HMM supervector is constructed by st...
متن کامل