Impact of deep mlp architecture on different acoustic modeling techniques for under-resourced speech recognition

Posterior based acoustic modeling techniques such as Kullback– Leibler divergence based HMM (KL-HMM) and Tandem are able to exploit out-of-language data through posterior fea-tures, estimated by a Multi-Layer Perceptron (MLP). In this paper, we investigate the performance of posterior based ap-proaches in the context of under-resourced speech recognition when a standard three-layer MLP is replaced by a deeper five-layer MLP. The deeper MLP architecture yields similar gains of about 15 % (relative) for Tandem, KL-HMM as well as for a hybrid HMM/MLP system that directly uses the poste-rior estimates as emission probabilities. The best performing system, a bilingual KL-HMM based on a deep MLP, jointly trained on Afrikaans and Dutch data, performs 13 % better than a hybrid system using the same bilingual MLP and 26% better than a subspace Gaussian mixture system only trained on Afrikaans data. Index Terms — KL-HMM, Tandem, hybrid system, deep MLPs, under-resourced speech recognitio