Successive speaker adaptation for multiplication type FVQ/HMM.
نویسندگان
چکیده
منابع مشابه
Eigenvoices for speaker adaptation
We have devised a new class of fast adaptation techniques for speech recognition, based on prior knowledge of speaker variation. To obtain this prior knowledge, one applies Principal Component Analysis (PCA) [9] or a similar technique to a training set of T vectors of dimension D derived from T speaker-dependent (SD) models. This offline step yields T basis vectors, which we call “eigenvoices” ...
متن کاملCorrective training for speaker adaptation
This paper reports results on an experiment to use corrective training techniques for rapid acoustic speaker adaptation in a semi-continuous speech recognition system. Decoder output is used to adjust HMM acoustic models to improve discrimination between correct words and near misses. Twenty sentences are used as an adaptation set. A speech recognizer is run on each utterance to generate a word...
متن کاملDiscriminative adaptation for speaker verification
This paper describes a speaker verification system in which the talker and imposter models are adapted to achieve maximum discrimination, or equivalently minimum verification error. This goal is accomplishedby extending the minimum error classificationcriterion (MCE) and generalized probabilistic descent (GPD) algorithm to the task of adapting talker model parameters and the corresponding anti-...
متن کاملDiscriminative adaptation for speaker verification
Speaker verification is a binary classification task to determine whether a claimed speaker uttered a phrase. Current approaches to speaker verification tasks typically involve adapting a general speaker Universal Background Model (UBM), normally a Gaussian Mixture Model (GMM), to model a particular speaker. Verification is then performed by comparing the likelihoods from the speaker model to t...
متن کاملSuccessive cohort selection (SCS) for text-independent speaker verification
A novel cohort selection method, namely, successive cohort selection (SCS) is presented in this paper for text-independent speaker verification. The proposed method computes distance between two models directly and it selects new cohort member based on both the claimed speaker model and the existing cohort members. In addition to this new cohort selection method, we also propose a new score mea...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Acoustical Science and Technology
سال: 2002
ISSN: 1346-3969,1347-5177
DOI: 10.1250/ast.23.339