pith. sign in

arxiv: 2008.05760 · v1 · pith:NVYOCYV6 · submitted 2020-08-13 · cs.CL · cs.LG

MASRI-HEADSET: A Maltese Corpus for Speech Recognition

pith:NVYOCYV6open to challenge →

classification cs.CL cs.LG
keywords maltesecorpusspeechmasri-headsetmaltarecognitionspokentext
0
0 comments X
read the original abstract

Maltese, the national language of Malta, is spoken by approximately 500,000 people. Speech processing for Maltese is still in its early stages of development. In this paper, we present the first spoken Maltese corpus designed purposely for Automatic Speech Recognition (ASR). The MASRI-HEADSET corpus was developed by the MASRI project at the University of Malta. It consists of 8 hours of speech paired with text, recorded by using short text snippets in a laboratory environment. The speakers were recruited from different geographical locations all over the Maltese islands, and were roughly evenly distributed by gender. This paper also presents some initial results achieved in baseline experiments for Maltese ASR using Sphinx and Kaldi. The MASRI-HEADSET Corpus is publicly available for research/academic purposes.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.