Capítulo de livro Revisado por pares

Automatic Turn-Level Language Identification for Code-Switched Spanish–English Dialog

2019; Springer Science+Business Media; Linguagem: Inglês

10.1007/978-981-13-9443-0_5

ISSN

1876-1119

Autores

Vikram Ramanarayanan, Robert Pugh, Yao Qian, David Suendermann‐Oeft,

Tópico(s)

Speech Recognition and Synthesis

Resumo

We examine the efficacy of text and speech-based features for language identification in code-switched human-human dialog interactions at the turn level. Ramanarayanan, Vikram We extract a variety of character- and word-based text features and pass them into multiple learners, including conditional random fields, logistic regressors and deep neural networks. Pugh, Robert We observe that our best-performing text system significantly outperforms a majority vote baseline. Qian, Yao We further leverage the popular i-Vector approach in extracting features from the speech signal and show that this outperforms a traditional spectral feature-based front-end as well as the majority vote baseline. Suendermann-Oeft, David

Referência(s)