This paper addresses the problem of finding a subset of the acoustic feature space that best represents the phoneme set used in a speech recognition system. A maximum mutual information approach is presented for selecting acoustic features to be combined together to represent the distinctions among the phonemes. The overall phoneme recognition accuracy is slightly increased for the same length ...

We present a feature extraction technique for automatic speech recognition that uses Tandem representation of short-term spectral envelope and modulation frequency features. These features, derived from sub-band temporal envelopes of speech estimated using frequency domain linear prediction, are combined at the phoneme posterior level. Tandem representations derived from these phoneme posterior...

We present a novel continuous speech recognition framework designed to unite the principles of triphone and Long ShortTerm Memory (LSTM) modeling. The LSTM principle allows a recurrent neural network to store and to retrieve information over long time periods, which was shown to be well-suited for the modeling of co-articulation effects in human speech. Our system uses a bidirectional LSTM netw...

This paper presents a new approach to phoneme recognition using nonsequential sub{phoneme units. These units are called acoustic events and are phonologically meaningful as well as recognizable from speech signals. Acoustic events form a phonologically incomplete representation as compared to distinctive features. This problem may partly be overcome by incorporating phonological constraints. Cu...

Unsupervised cluster adaptive training of acoustic models offers promise in improving recognition accuracy, especially for speech recognition systems that store massive sets of speech samples from unknown people. How to classify the variety of acoustic characteristics is an important problem in adaptation sample clustering. We propose a novel speech sample clustering method that focuses on the ...

This paper discusses hidden Markov model-based context-dependent phoneme modelling and their associated problems, particulary data insufficiency and unseen triphones. The implementation of decision tree-based state clustering, a technique suitable for solving these problems, is discussed. This technique was first proposed in 1994 by Young, Woodland and Odell [1]. A triphone-based phoneme recogn...

Discriminative training techniques for Hidden Markov Models were recently proposed and successfully applied for automatic speech recognition In this paper a discussion of the Minimum Classi cation Error and the Maximum Mu tual Information objective is presented An extended reesti mation formula is used for the HMM parameter update for both objective functions The discriminative training me thod...

In a spontaneous spoken dialogue understanding system, real-time response and robustness to the environment are required. To realize these requirements, we adopted a multi-agent system architecture. In this paper, we propose a reinforcement learning method for a phoneme recognizing agent as a sample agent, and adopt a continuous dynamic programming technique to deal with continuous phoneme reco...

This paper describes a novel method to improve the performance of second language speech recognition when the mother tongue of users is known. Considering that second language speech usually includes less fluent pronunciation and more frequent pronunciation mistakes, I propose using a reduced phoneme set generated by a phonetic decision tree (PDT)-based top-down sequential splitting method inst...