Improved Gender Independent Speaker Recognition Using Convolutional Neural Network Based Bottleneck Features
نویسندگان
چکیده
This paper proposes a novel framework to improve performance of gender independent i-Vector PLDA based speaker recognition using convolutional neural network (CNN). Convolutional layers of a CNN offer robustness to variations in input features including those due to gender. A CNN is trained for ASR with a linear bottleneck layer. Bottleneck features extracted using the CNN are then used to train a gender-independent UBM to obtain frame posteriors for training an i-Vector extractor matrix. To preserve speaker specific information, a hybrid approach to training the i-Vector extractor matrix using MFCC features with corresponding frame posteriors derived from bottleneck features is proposed. On the NIST SRE10 C5 condition pooled trials, our approach reduces the EER and minDCF 2010 by +14.62% and +14.42% respectively compared to a standard mfcc based gender-independent speaker recognition system.
منابع مشابه
شبکه عصبی پیچشی با پنجرههای قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کاملAn 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 کاملSpeech Emotion Recognition Using Scalogram Based Deep Structure
Speech Emotion Recognition (SER) is an important part of speech-based Human-Computer Interface (HCI) applications. Previous SER methods rely on the extraction of features and training an appropriate classifier. However, most of those features can be affected by emotionally irrelevant factors such as gender, speaking styles and environment. Here, an SER method has been proposed based on a concat...
متن کاملSpeaker adaptation of convolutional neural network using speaker specific subspace vectors of SGMM
The recent success of convolutional neural network (CNN) in speech recognition is due to its ability to capture translational variance in spectral features while performing discrimination. The CNN architecture requires correlated features as input and thus fMLLR transform which is estimated in de-correlated feature space fails to give significant improvement. In this paper, we propose two metho...
متن کاملInvestigating factor analysis features for deep neural networks in noisy speech recognition
The problem of speaker and channel adaptation in deep neural network (DNN) based automatic speech recognition (ASR) systems is of substantial interest in advancing the performance of these systems. Recently, the speaker identity vectors (i-vectors) have shown improvements for ASR systems in matched conditions. In this paper, we propose the application of the general factor analysis framework fo...
متن کامل