Abstract. This paper investigates the use of features based on posterior probabilities of subword units such as phonemes. These features are typically transformed when used as inputs for a hidden Markov model with mixture of Gaussians as emission distribution (HMM/GMM). In this work, we introduce a novel acoustic model that avoids the Gaussian assumption and directly uses posterior features without any transformation. This model is described by a finite state machine where each state is characterized by a target distribution and the cost function associated to each state is given by the Kullback-Leibler (KL) divergence between its target distribution and the posterior features. Furthermore, hybrid HMM/ANN system can be seen as a particular case of this KL-based model where state target distributions are predefined. A training method is also presented that minimizes the KL-divergence between the state target distributions and the posteriors features.

Abstract. The use of large speech corpora in example-based approaches for speech recognition is mainly focused on increasing the number of examples. This strategy presents some difficulties because databases may not provide enough examples for some rare words. In this paper we present a different method to incorporate the information contained in such corpora in these examplebased systems. A multilayer perceptron is trained on these databases to estimate speaker and task-independent phoneme posterior probabilities, which are used as speech features. By reducing the variability of features, fewer examples are needed to properly characterize a word. In this way, performance can be highly improved when limited number of examples is available. Moreover, we also study posterior-based local distances, these result more effective than traditional Euclidean distance. Experiments on Phonebook database support the idea that posterior features with a proper local distance can yield competitive results.

Posterior probabilities of sub-word units have been shown to be an effective front-end for ASR. However, attempts to model this type of features either do not benefit from modeling context-dependent phonemes, or use an inefficient distribution to estimate the state likelihood. This paper presents a novel acoustic model for posterior features that overcomes these limitations. The proposed model can be seen as a HMM where the score associated with each state is the KL divergence between a distribution characterizing the state and the posterior features from the test utterance. This KL-based acoustic model establishes a framework where other models for posterior features such as hybrid HMM/MLP and discrete HMM can be seen as particular cases. Experiments on the WSJ database show that the KL-based acoustic model can significantly outperform these latter approaches. Moreover, the proposed model can obtain comparable results to complex systems, such as HMM/GMM, using significantly fewer parameters.

This paper presents a novel approach for those applications where vocabulary is defined by a set of acoustic samples. In this approach, the acoustic samples are used as reference templates in a template matching framework. The features used to describe the reference templates and the test utterances are estimates of phoneme posterior probabilities. These posteriors are obtained from a MLP trained on an auxiliary database. Thus, the speech variability present in the features is reduced by applying the speech knowledge captured by the MLP on the auxiliary database. Moreover, information theoretic dissimilarity measures can be used as local distances between features.When compared to state-of-the-art systems, this approach outperforms acoustic-based techniques and obtains comparable results to orthography-based methods. The proposed method can also be directly combined with other posterior-based HMM systems. This combination successfully exploits the complementarity between templates and parametric models.