This paper introduces the USPDATRO dataset. This is a speech dataset, in the Romanian language, constructed from open data, focusing on under-represented voice types (children, young and old people, and female voices). The paper covers the methodology behind the dataset construction, specific details regarding the dataset, and evaluation of existing Romanian Automatic Speech Recognition (ASR) systems, with different architectures. Results indicate that more under-represented speech content is needed in the training of ASR systems. Our approach can be extended to other low-resourced languages, as long as open data are available.

Transformer models produce advanced text representations that have been used to break through the hard challenge of natural language understanding. Using the Transformer’s attention mechanism, which acts as a language learning memory, trained on tens of billions of words, a word sense disambiguation (WSD) algorithm can now construct a more faithful vectorial representation of the context of a word to be disambiguated. Working with a set of 34 lemmas of nouns, verbs, adjectives and adverbs selected from the National Reference Corpus of Romanian (CoRoLa), we show that using BERT’s attention heads at all hidden layers, we can devise contextual vectors of the target lemma that produce better clusters of lemma’s senses than the ones obtained with standard BERT embeddings. If we automatically translate the Romanian example sentences of the target lemma into English, we show that we can reliably infer the number of senses with which the target lemma appears in the CoRoLa. We also describe an unsupervised WSD algorithm that, using a Romanian BERT model and a few example sentences of the target lemma’s senses, can label the Romanian induced sense clusters with the appropriate sense labels, with an average accuracy of 64%.

Within the larger project ROBIN, focused on the development of software and services for human-robot interaction, we present here a set of activities focused on the creation and enhancement of language resources necessary for making dialogue possible between humans and the robot Pepper. More precisely, we describe the preparatory activities for turning the robot Pepper into a dialog partner for a human by using the Romanian language. The language resources that have been created are a lexicon, a language model, and an acoustic language model. They have been enhanced by using other language resources, such as the Romanian wordnet and word embeddings extracted from the large Romanian reference corpus CoRoLa. They will ensure oral communication within some envisaged microworlds, thus they are specific to these microworlds. These resources have been carefully curated and evaluated.