This paper aims to provide a summary of the existing corpora of spoken Bulgarian. The
corpora are examined for their scope, genre, speech spontaneity, presence of phonetic …

This paper presents the methodology we applied for building a new corpus of Bulgarian
speech suitable for training and evaluating modern speech recognition systems. The …

In this paper we introduce a Bulgarian speech database, which was created for the purpose
of ASR technology development. The paper describes the design and the content of the …

The paper presents the results of a project completed by the authors for realizing a
continuous speech recognition system for Bulgarian. The state-of-the-art speech recognition …

We present the design, implementation and assessment of a high-quality unit-selection
speech synthesis system for Bulgarian which, to the best of the authors' knowledge, is the …

Verbalization of non-lexical linguistic units plays an important role in language modeling for
automatic speech recognition systems. Most verbalization methods require valuable …

The accurate placement of word stress is a critical component of the correct pronunciation of
words. Contemporary publicly available text-to-speech (TTS) datasets have a relatively …

The meaning of the terms Natural Language Processing and Computational Linguistics can
be interpreted in different ways. Linguistics, in contrast to the other sciences, began to use …

The paper discusses some problems of mathematics and computer sciences education for
students suffering from vision loss. The groups of devices to support training, the …