The cascade HMM/ANN hybrid: A new framework for discriminative training in speech recognition
نویسندگان
چکیده
In this paper, a new formulation for discriminative training of HMMs is presented. This formulation uses a properly trained MLP in a simple interconnection with HMMs called “Cascade HMM/ANN Hybrid”. Our training algorithm has simple realization in comparison with other discriminative training for HMMs such as MDI and MMI. We also present a rigid mathematical proof of its convergence. We found that using cascade HMM/ANN for isolated word recognition in noisy environment results in increasing the recognition accuracy from 93.3% in classic HMMs to 99.1% using a two layer MLP. No significant increase in computational requirements is needed in recognition phase. Both theoretical and experimental achievements are included in the paper.
منابع مشابه
Hybrid HMM/Neural Network based Speech Recognition in Loquendo ASR
This paper describes hybrid Hidden Markov Models / Artificial Neural Networks (HMM/ANN) models devoted to speech recognition, and in particular Loquendo HMM/ANN, that is the core of Loquendo ASR. While Hidden Markov Models (HMM) is a dominant approach in most state-of-the-art speaker-independent, continuous speech recognition systems (and commercial products), Artificial Neural Networks (ANN) a...
متن کاملDiscriminative and Connectionist Methods for Speech Processing
Discriminative methods for speech include using criteria such as MMI (maximum mutual information) and MCE (minimum classification error) during the training of HMMs (hidden Markov models). Connectionist methods bring to mind the use of ANNs (artificial neural networks). These methods are in fact closely related, sharing common solutions for tackling the complex problem of how to design MAP (max...
متن کاملSpeech enhancement based on hidden Markov model using sparse code shrinkage
This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...
متن کاملA NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction
This paper deals with a hybrid NN/HMM architecture for continuous speech recognition. We present a novel approach to set up a neural linear or nonlinear feature transformation that is used as a preprocessor on top of the HMM system’s RBF-network to produce discriminative feature vectors that are well suited for being modeled by mixtures of Gaussian distributions. In order to omit the computatio...
متن کاملOff-line Arabic Handwritten Recognition Using a Novel Hybrid HMM-DNN Model
In order to facilitate the entry of data into the computer and its digitalization, automatic recognition of printed texts and manuscripts is one of the considerable aid to many applications. Research on automatic document recognition started decades ago with the recognition of isolated digits and letters, and today, due to advancements in machine learning methods, efforts are being made to iden...
متن کامل