Discriminative speaker adaptation with conditional maximum likelihood linear regression
نویسندگان
چکیده
We present a simplified derivation of the extended Baum-Welch procedure, which shows that it can be used for Maximum Mutual Information (MMI) of a large class of continuous emission density hidden Markov models (HMMs). We use the extended Baum-Welch procedure for discriminative estimation of MLLR-type speaker adaptation transformations. The resulting adaptation procedure, termed Conditional Maximum Likelihood Linear Regression (CMLLR), is used successfully for supervised and unsupervised adaptation tasks on the Switchboard corpus, yielding an improvement over MLLR. The interaction of unsupervised CMLLR with segmental minimum Bayes risk lattice voting procedures is also explored, showing that the two procedures are complimentary.
منابع مشابه
Discriminative adaptation for log-linear acoustic models
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian models, and a more direct parametrisation of the posterior model. To competitively use log-linear models for speech recognition, important methods, such as speaker adaptation, have to be reformulated in a log-linear f...
متن کاملDiscriminative Fuzzy Clustering Maximum a Posterior Linear Regression for Speaker Adaptation
We propose a discriminative fuzzy clustering maximum a posterior linear regression (DFCMAPLR) model adaptation approach to compensate the acoustic mismatch due to speaker variability. The DFCMAPLR approach adopts the MAP criterion and a discriminative objective function to estimate shared affine transform and fuzzy weight sets, respectively. Then, through a linear combination of the calculated ...
متن کاملSmoothing Factor in Discriminative Feature Adaptation
In these days, Discriminative Training (DT) methods of an acoustics model are taking over the leadership in the speaker recognition task for training an acoustics model. Maximum Likelihood (ML) training suffers from some inaccuracies because of improper assumptions of the suitability of the HMM. Well-known adaptation method, feature Maximum Likelihood Linear Regression (fMLLR), is based on ML c...
متن کاملDiscriminative Linear Transforms for Speaker Adaptation
Linear transform adaptation techniques such as Maximum Likelihood Linear Regression (MLLR) are a popular and effective family of methods for speaker adaptation. MLLR estimates transform parameters for Gaussian means and variances using a maximum likelihood (ML) objective function. This paper discusses the use of an alternative discriminative objective function for linear transform estimation, w...
متن کاملA study on soft margin estimation of linear regression parameters for speaker adaptation
We formulate a framework for soft margin estimation-based linear regression (SMELR) and apply it to supervised speaker adaptation. Enhanced separation capability and increased discriminative ability are two key properties in margin-based discriminative training. For the adaptation process to be able to flexibly utilize any amount of data, we also propose a novel interpolation scheme to linearly...
متن کامل