Model-space MLLR for trajectory HMMs
نویسندگان
چکیده
This paper proposes model-space Maximum Likelihood Linear Regression (mMLLR) based speaker adaptation technique for trajectory HMMs, which have been derived from HMMs by imposing explicit relationships between static and dynamic features. This model can alleviate two limitations of the HMM: constant statistics within a state and conditional independence assumption of state output probabilities without increasing the number of model parameters. Results in a continuous speech recognition experiments show that the proposed algorithm can adapt trajectory HMMs to a specific speaker and improve the performance of a trajectory HMM-based speech recognition system.
منابع مشابه
Speaker adaptation of trajectory HMMs using feature-space MLLR
Recently, a trajectory model, derived from the hidden Markov model (HMM) by imposing explicit relationships between static and dynamic features, has been proposed. The derived model, named trajectory HMM, can alleviate two limitations of the HMM: constant statistics within a state and conditional independence assumption of state output probabilities. In the present paper, a speaker adaptation a...
متن کاملAdaptation of pitch and spectrum for HMM-based speech synthesis using MLLR
This paper describes a technique for synthesizing speech with an arbitrary speaker characteristics using speaker independent speech units, which we call “average voice” units. The technique is based on an HMM-based text-to-speech (TTS) system and MLLR adaptation algorithm. In the HMM-based TTS system, speech synthesis units are modeled by multi-space probability distribution (MSD) HMMs which ca...
متن کاملRobust speaker adaptation of continuous density HMMS using multilayer perceptron network
The performance of global affine and nonlinear transformations for speaker adaptation in a hidden Markov model (HMM) speech recognition system are compared in this paper. The nonlinear transformation was obtained with a multilayer perceptron network (MLP) which was trained during the adaptation process to transform the mean vectors of the HMMs such that the output probabilities of the HMMs for ...
متن کاملIntegration of MLLR adaptation with pronunciation proficiency adaptation for non-native speech recognition
To recognize non-native speech, larger acoustic/linguistic distortions must be handled adequately in acoustic modeling, language modeling, lexical modeling, and/or decoding strategy. In this paper, a novel method to enhance MLLR adaptation of acoustic models for non-native speech recognition is proposed. In the case of native speech recognition, MLLR speaker adaptation was successfully introduc...
متن کاملDetection of social speech signals using adaptation of segmental HMMs
This paper proposes an approach to detect social speech signals by computing segmental features using adaptation of segmental Hidden Markov Models (HMMs). This approach uses segmental HMMs and model adaptation techniques such as Maximum Likelihood Linear Regression (MLLR) and Maximum A Posterior (MAP) in order to acquire specific (or adapted) segmental HMMs that are fine-tuned to detect local r...
متن کامل