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 speech database. We present also an empirical evaluation of the performance of a LVCSR system for Bulgarian trained on the BulPhonC data. The resource is available free for scientific usage.
@InProceedings{HATEVA16.478,
author = {Neli Hateva and Petar Mitankin and Stoyan Mihov}, title = {BulPhonC: Bulgarian Speech Corpus for the Development of ASR Technology}, booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)}, year = {2016}, month = {may}, date = {23-28}, location = {Portorož, Slovenia}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Sara Goggi and Marko Grobelnik and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {978-2-9517408-9-1}, language = {english} }
Summary of the paper