Discriminative MLPs in HMM-based recognition of speech in cellular telephony
نویسندگان
چکیده
Deviating from the conventional Hidden Markov ModelMulti-Layer Perceptron (HMM-MLP) hybrid paradigm of using MLP for classi cation, the proposed discriminative MLP technique uses MLP as a mapping module for feature extraction for conventional HMM-based systems. The MLP is discriminatively trained on the phonetically labeled training data to generate the phoneme posterior probabilities. We achieved a relative word error rate reduction of 15-35% on AURORA Phase 2 continuous digit recognition task de ned by ETSI.
منابع مشابه
Discriminative optimization of large vocabulary Mandarin conversational speech recognition system
This paper examines techniques of discriminative optimization for acoustic model, including both HMM parameters and linear transforms, in the context of HUB5 Mandarin large vocabulary speech recognition task, with the aim to partly solve the problems brought by the sparseness and the highly ambiguous nature of the telephony conversational speech data. Three techniques are studied: MMI training ...
متن کاملThe efficient incorporation of MLP features into automatic speech recognition systems
In recent years, the use of Multi-Layer Perceptron (MLP) derived acoustic features has become increasingly popular in automatic speech recognition systems. These features are typically used in combination with standard short-term spectral-based features, and have been found to yield consistent performance improvements. However there are a number of design decisions and issues associated with th...
متن کاملContext-Dependent Multiple Distribution Phonetic Modeling with MLPs
Berkeley, CA 94704 Victor Abrash SRI International A number of hybrid multilayer perceptron (MLP)/hidden Markov model (HMM:) speech recognition systems have been developed in recent years (Morgan and Bourlard. 1990). In this paper. we present a new MLP architecture and training algorithm which allows the modeling of context-dependent phonetic classes in a hybrid MLP/HMM: framework. The new trai...
متن کاملComparison and Combination of Multilayer Perceptrons and Deep Belief Networks in Hybrid Automatic Speech Recognition Systems
To improve the speech recognition performance, many ways to augment or combine HMMs (Hidden Markov Models) with other models to build hybrid architectures have been proposed. The hybrid HMM/ANN (Hidden Markov Model / Artificial Neural Network) architecture is one of the most successful approaches. In this hybrid model, ANNs (which are often multilayer perceptron neural networks MLPs) are used a...
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