Related papers: Generative Adversarial Speaker Embedding Networks …
Cross-lingual speech emotion recognition (SER) is a crucial task for many real-world applications. The performance of SER systems is often degraded by the differences in the distributions of training and test data. These differences become…
In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…
In this paper we describe the recent advancements made in the IBM i-vector speaker recognition system for conversational speech. In particular, we identify key techniques that contribute to significant improvements in performance of our…
Performance degradation caused by language mismatch is a common problem when applying a speaker verification system on speech data in different languages. This paper proposes a domain transfer network, named EDITnet, to alleviate the…
Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different…
Linear Discriminant Analysis (LDA) has been used as a standard post-processing procedure in many state-of-the-art speaker recognition tasks. Through maximizing the inter-speaker difference and minimizing the intra-speaker variation, LDA…
In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing…
This work presents a novel back-end framework for speaker verification using graph attention networks. Segment-wise speaker embeddings extracted from multiple crops within an utterance are interpreted as node representations of a graph. The…
Speaker verification is an established yet challenging task in speech processing and a very vibrant research area. Recent speaker verification (SV) systems rely on deep neural networks to extract high-level embeddings which are able to…
Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…
Adversarial training of end-to-end (E2E) ASR systems using generative adversarial networks (GAN) has recently been explored for low-resource ASR corpora. GANs help to learn the true data representation through a two-player min-max game.…
The x-vector based deep neural network (DNN) embedding systems have demonstrated effectiveness for text-independent speaker verification. This paper presents a multi-task learning architecture for training the speaker embedding DNN with the…
Learning robust speaker embeddings is a crucial step in speaker diarization. Deep neural networks can accurately capture speaker discriminative characteristics and popular deep embeddings such as x-vectors are nowadays a fundamental…
In this paper we propose a novel defense approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo. Unlike conventional defense approaches, the proposed approach does not…
The classification of acoustic environments allows for machines to better understand the auditory world around them. The use of deep learning in order to teach machines to discriminate between different rooms is a new area of research.…
Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep…
Deep speaker embedding has demonstrated state-of-the-art performance in speaker recognition tasks. However, one potential issue with this approach is that the speaker vectors derived from deep embedding models tend to be non-Gaussian for…
Many neural network speaker recognition systems model each speaker using a fixed-dimensional embedding vector. These embeddings are generally compared using either linear or 2nd-order scoring and, until recently, do not handle…
Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…
Recently several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short…