相关论文: Data augmentation versus noise compensation for x-…

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…

A deep neural network (DNN)-based speech enhancement (SE) aiming to maximize the performance of an automatic speech recognition (ASR) system is proposed in this paper. In order to optimize the DNN-based SE model in terms of the character…

Significant progress has recently been made in speaker diarisation after the introduction of d-vectors as speaker embeddings extracted from neural network (NN) speaker classifiers for clustering speech segments. To extract better-performing…

Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly. Noisy student training is an iterative self-training method that…

Speech enhancement methods are commonly believed to improve the performance of automatic speech recognition (ASR) in noisy environments. However, the effectiveness of these techniques cannot be taken for granted in the case of modern…

The paper introduces Diff-Filter, a multichannel speech enhancement approach based on the diffusion probabilistic model, for improving speaker verification performance under noisy and reverberant conditions. It also presents a new two-step…

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…

As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services. In this paper, we propose…

Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains…

Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it…

In this paper, we address the generalization of deep neural network (DNN) based speech enhancement to unseen noise conditions for the case that training data is limited in size and diversity. To gain more insights, we analyze the…

The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error loss between the DNN's…

The success of deep learning has sparked significant interest in designing computer hardware optimized for the high computational demands of neural network inference. As further miniaturization of digital CMOS processors becomes…

This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to…

We present a Bayesian formulation for deep speaker embedding, wherein the xi-vector is the Bayesian counterpart of the x-vector, taking into account the uncertainty estimate. On the technology front, we offer a simple and straightforward…

Conversational speech not only contains several variants of neutral speech but is also prominently interlaced with several speaker generated non-speech sounds such as laughter and breath. A robust speaker recognition system should be…

While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many scenarios, only noisy speech of a target speaker is available,…

Background noise is a major source of quality impairments in Voice over Internet Protocol (VoIP) and Public Switched Telephone Network (PSTN) calls. Recent work shows the efficacy of deep learning for noise suppression, but the datasets…

This paper investigates the effects of limited speech data in the context of speaker verification using deep neural network (DNN) approach. Being able to reduce the length of required speech data is important to the development of speaker…