Automatic language identification in broadcast news

Author

Backfried, Gerhard ; Rainoldi, Rainiero ; Riedler, Jürgen

Author_Institution

Speech, Artificial Intelligence & Language Labs., Vienna, Austria

Volume

2

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

1406

Lastpage

1410

Abstract

We present experiments on automatic language identification in the broadcast news domain. Because of the inherent diversity of news broadcasts, speech is extracted from the raw audio data by means of phone-level decoding using broad classes of phonemes. Training and testing was performed on recordings of German, English, Spanish and French news shows from a variety of European TV channels. Each language is characterized by a Gaussian mixture model solely created from corresponding acoustic features. The overall average error rate on speech segments is 16.32%. The current system disregards (almost) any kind of linguistic information; however, it is therefore easily extensible to new languages

Keywords

Gaussian distribution; broadcasting; decoding; languages; neural nets; speech processing; English language; European TV channels; French language; Gaussian mixture model; German language; Spanish language; acoustic features; automatic language identification; broadcast news; error rate; neural nets; phone-level decoding; phonemes; raw audio data; recordings; speech extraction; speech segments; television; Acoustic testing; Broadcasting; Context modeling; Data mining; Decoding; Hidden Markov models; Natural languages; Rhythm; Speech; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007722

Filename

1007722