AN Em-BASED ALGORITHM FOR LEARNING STATISTICAL HIDDEN DYNAMIC MODEL PARAMETERS FOR PHONETIC RECOGNITION
نویسندگان
چکیده
This paper presents a new parameter estimation algorithm based on the Extended Kalman Filter (EKF) for the recently proposed statistical coarticulatory Hidden Dynamic Model (HDM). We show how the EKF parameter estimation algorithm unifies and simplifies the estimation of both the state and parameter vectors. Experiments based on N-best rescoring demonstrate superior performance of the (contextindependent) HDM over a triphone baseline HMM in the TIMIT phonetic recognition task. We also show that the HDM is capable of generating speech vectors close to those from the corresponding real data.
منابع مشابه
An EKF-based algorithm for learning statistical hidden dynamic model parameters for phonetic recognition
This paper presents a new parameter estimation algorithm based on the Extended Kalman Filter (EKF) for the recently proposed statistical coarticulatory Hidden Dynamic Model (HDM). We show how the EKF parameter estimation algorithm unifies and simplifies the estimation of both the state and parameter vectors. Experiments based on N-best rescoring demonstrate superior performance of the (contexti...
متن کاملSpeech Recognition with Dynamic Bayesian Networks
Dynamic Bayesian networks (DBNs) are a useful tool for representing complex stochastic processes. Recent developments in inference and learning in DBNs allow their use in real-world applications. In this paper, we apply DBNs to the problem of speech recognition. The factored state representation enabled by DBNs allows us to explicitly represent long-term articulatory and acoustic context in add...
متن کاملمقایسه روش های طیفی برای شناسایی زبان گفتاری
Identifying spoken language automatically is to identify a language from the speech signal. Language identification systems can be divided into two categories, spectral-based methods and phonetic-based methods. In the former, short-time characteristics of speech spectrum are extracted as a multi-dimensional vector. The statistical model of these features is then obtained for each language. The ...
متن کاملStatistical Optimization of Acoustic Models for Large Vocabulary Speech Recognition
This dissertation investigates statistical optimization of acoustic models in speech recognition. Two new optimization methods are proposed for phonetic decision tree (PDT) search and Hidden Markov modeling (HMM)-the knowledge-based adaptive PDT algorithm and the HMM gradient boosting algorithm. Investigations are conducted to applying both methods to improve word error rate of the state-of-the...
متن کاملA dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition
An overview of a statistical paradigm for speech recognition is given where phonetic and phonological knowledge sources, drawn from the current understanding of the global characteristics of human speech communication, are seamlessly integrated into the structure of a stochastic model of speech. A consistent statistical formalism is presented in which the submodels for the discrete, feature-bas...
متن کامل