Language score calibration using adapted Gaussian back-end
نویسندگان
چکیده
Generative Gaussian back-end and discriminative logistic regression are the most used approaches for language score fusion and calibration. Combination of these two approaches can significantly improve the performance. This paper proposes the use of an adapted Gaussian back-end, where the mean of the language-dependent Gaussian is adapted from the mean of a language-specific background Gaussian viamaximum a posteriori estimation algorithm. Experiments are conducted using the LRE-07 evaluation data. Compared to the conventional Gaussian back-end approach for a closed set task, relative improvements in the Cavg of 50%, 17% and 4.2% are obtained on the 30s, 10s and 3s conditions, respectively. Besides this, the estimated scores are better calibrated. A combination with logistic regression results in a system with the best calibrated scores.
منابع مشابه
Multiclass Discriminative Training of i-vector Language Recognition
The current state-of-the-art for acoustic language recognition is an i-vector classifier followed by a discriminatively-trained multiclass back-end. This paper presents a unified approach, where a Gaussian i-vector classifier is trained using Maximum Mutual Information (MMI) to directly optimize the multiclass calibration criterion, so that no separate back-end is needed. The system is extended...
متن کاملStudents’ Attitude Towards English Language Learning: The Case of Iranian Junior High-School Students and Prospects Course-books
Although a surfeit of studies have examined the students’ attitude towards foreign and / or second language both inside and outside Iran, it seems scanty studies have been devoted to evaluate Prospect-trained students’ attitude towards English. This quantitative study investigated the students’ attitudes towards English language learning among 80 junior high school students in Ahvaz, Iran. Thes...
متن کاملDetection target dependent score calibration for language recognition
Based on the conventional score calibration techniques with gaussian backend and logistic regression of the relative likelihood scores, this paper proposes a method of score calibration specific to a subset of related languages. Detection scores to two related languages are considered as two sources with similar and complementary information. In the proposed score calibration, an optimal linear...
متن کاملAutomatic Language Identification with Discriminative Language Characterization Based on SVM
Robust automatic language identification (LID) is the task of identifying the language from a short utterance spoken by an unknown speaker. The mainstream approaches include parallel phone recognition language modeling (PPRLM), support vector machine (SVM) and the general Gaussian mixture models (GMMs). These systems map the cepstral features of spoken utterances into high level scores by class...
متن کاملNuance - Politecnico di torino's 2012 NIST speaker recognition evaluation system
This paper describes the Nuance–Politecnico di Torino (NPT) speaker recognition system submitted to the NIST SRE12 evaluation campaign. Included are the results of postevaluation tests, focusing on the analysis of the effects of score normalization and condition-dependent calibration. The submitted system combines the results of five acoustic recognizers all based on Gaussian Mixture Models (GM...
متن کامل