The 2015 NIST Language Recognition Evaluation: The Shared View of I2R, Fantastic4 and SingaMS
نویسندگان
چکیده
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, Fantastic4, 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.
منابع مشابه
NIST language recognition evaluation - plans for 2015
We discuss two NIST coordinated evaluations of automatic language recognition technology planned for calendar year 2015 along with possible additional plans for the future. The first is the Language Recognition i-Vector Machine Learning Challenge, largely modeled on the 2013-2014 Speaker Recognition i-Vector Machine Learning Challenge. This online challenge, emphasizing the language identificat...
متن کاملResults of The 2015 NIST Language Recognition Evaluation
In 2015, NIST conducted the most recent in an ongoing series of Language Recognition Evaluations (LRE) meant to foster research in language recognition. The 2015 Language Recognition Evaluation featured 20 target languages grouped into 6 language clusters. The evaluation was focused on distinguishing languages within each cluster, without disclosing which cluster a test language belongs to. The...
متن کاملSpeaker Diarization Using Direction of Arrival Estimate and Acoustic Feature Information: The I2R-NTU Submission for the NIST RT 2007 Evaluation
This paper describes the IR/NTU system submitted for the NIST Rich Transcription 2007 (RT-07) Meeting Recognition evaluation Multiple Distant Microphone (MDM) task. In our system, speaker turn detection and clustering is done using Direction of Arrival (DOA) information. Purification of the resultant speaker clusters is then done by performing GMM modeling on acoustic features. As a final step,...
متن کاملLanguage Recognition for Dialects and Closely Related Languages
This paper describes our development work to design a language recognition system that can discriminate closely related languages and dialects of the same language. The work was a joint effort by LIMSI and Vocapia Research in preparation for the NIST 2015 Language Recognition Evaluation (LRE). The language recognition system results from a fusion of four core classifiers: a phonotactic componen...
متن کاملSpoken language recognition in conversational telephone speech and TV broadcast news (GLOSA)
In this brief communication we present the project GLOSA, financed by the Government of the Basque Country for the period 2010-2011. The project has two main technological objectives: (1) creating a suitable infrastructure for the development and evaluation of language recognition technologies; and (2) preparing a competitive language recognition system for conversational telephone speech, whic...
متن کامل