JSpeech: A Multi-Lingual Conversational Speech Corpus

Abstract

Speech processing, automatic speech and speaker recognition are the major area of interests in the field of computational linguistics. Research and development of computer and human interaction, forensic technologies and dialogue systems have been the motivating factor behind this interest. In this paper, JSpeech is introduced, a multilingual corpus. This corpus contains 1332 hours of conversational speech from 47 different languages. This corpus can be used in a variety of studies, created from 106 public chat group the effect of language variability on the performance of speaker recognition systems and automatic language detection. To this end, we include speaker verification results obtained for this corpus using a state of the art method based on 3D convolutional neural network.

Speaker Recognition Benchmark Using the CHiME-5 Corpus

“…A subset of the speakers also spoke English, which allows cross-lingual studies. Along this line, the JSpeech [6] multi-lingual corpus expands this area by providing 1332 hours of chat group conversational speech in 47 languages from 12140 speakers.…”