Multilingual bottleneck features for language recognition

نویسندگان

  • Radek Fér
  • Pavel Matejka
  • Frantisek Grézl
  • Oldrich Plchot
  • Jan Cernocký
چکیده

In this paper, we investigate Multilingual Stacked Bottleneck Features (SBN) in language recognition domain. These features are extracted using bottleneck neural networks trained on data from multiple languages. Previous results have shown benefits of multilingual training of SBN feature extractor for speech recognition. Here we focus on its impact on language recognition. We present results obtained with monolingual and multilingual networks, and their fusions. Using multilingual features, we obtain 16% relative improvement on 3 s condition of NIST LRE09 dataset with respect to features trained on a single language.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An Information-Theoretic Discussion of Convolutional Bottleneck Features for Robust Speech Recognition

Convolutional Neural Networks (CNNs) have been shown their performance in speech recognition systems for extracting features, and also acoustic modeling. In addition, CNNs have been used for robust speech recognition and competitive results have been reported. Convolutive Bottleneck Network (CBN) is a kind of CNNs which has a bottleneck layer among its fully connected layers. The bottleneck fea...

متن کامل

Investigation of bottleneck features and multilingual deep neural networks for speaker verification

Recently, the integration of deep neural networks (DNNs) with i-vector systems is proved to be effective for speaker verification. This method uses the DNN with senone outputs to produce frame alignments for sufficient statistics extraction. However, two types of data mismatch may degrade the performance of the DNN-based speaker verification systems. First, the DNN requires transcribed training...

متن کامل

Multilingual hierarchical MRASTA features for ASR

Recently, a multilingual Multi Layer Perceptron (MLP) training method was introduced without having to explicitly map the phonetic units of multiple languages to a common set. This paper further investigates this method using bottleneck (BN) tandem connectionist acoustic modeling for four high-resourced languages — English, French, German, and Polish. Aiming at the improvement of already existi...

متن کامل

Language ID-based training of multilingual stacked bottleneck features

In this paper, we explore multilingual feature-level data sharing via Deep Neural Network (DNN) stacked bottleneck features. Given a set of available source languages, we apply language identification to pick the language most similar to the target language, for more efficient use of multilingual resources. Our experiments with IARPA-Babel languages show that bottleneck features trained on the ...

متن کامل

Investigating the learning effect of multilingual bottle-neck features for ASR

Deep neural networks (DNNs) have become state-of-the-art techniques of automatic speech recognition in the last few years. They can be used at the preprocessing level (Tandem or BottleNeck features) or at the acoustic model level (hybrid Hidden Markov Model/DNN). Moreover, they allow exploiting multilingual data to improve monolingual systems. This paper presents our investigation of the learni...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015