The 2015 NIST Language Recognition Evaluation: The Shared View of I2R, Fantastic4 and SingaMS - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

The 2015 NIST Language Recognition Evaluation: The Shared View of I2R, Fantastic4 and SingaMS

Abstract

The series of language recognition evaluations (LRE's) conducted by the National Institute of Standards and Technology (NIST) have been one of the driving forces in advancing spoken language recognition technology. This paper presents a shared view of five institutions resulting from our collaboration toward LRE 2015 submissions under the names of I2R, Fan-tastic4, and SingaMS. Among others, LRE'15 emphasizes on language detection in the context of closely related languages, which is different from previous LRE's. From the perspective of language recognition system design, we have witnessed a major paradigm shift in adopting deep neural network (DNN) for both feature extraction and classifier. In particular, deep bottleneck features (DBF) have a significant advantage in replacing the shifted-delta-cepstral (SDC) which has been the only option in the past. We foresee deep learning is going to serve as a major driving force in advancing spoken language recognition system in the coming years.
Fichier principal
Vignette du fichier
0624_v2.pdf (232.68 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01433164 , version 1 (24-03-2017)

Identifiers

Cite

Kong Aik Lee, Haizhou Li, Li Deng, Ville Hautamäki, Wei Rao, et al.. The 2015 NIST Language Recognition Evaluation: The Shared View of I2R, Fantastic4 and SingaMS. Interspeech 2016, 2016, San Fransisco, United States. pp.3211 - 3215, ⟨10.21437/Interspeech.2016-624⟩. ⟨hal-01433164⟩
616 View
398 Download

Altmetric

Share

Gmail Facebook X LinkedIn More