Related papers: Dynamic Kernels and Channel Attention for Low Reso…
With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…
Deep learning algorithms have been known to be vulnerable to adversarial perturbations in various tasks such as image classification. This problem was addressed by employing several defense methods for detection and rejection of particular…
While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…
Most current speech technology systems are designed to operate well even in the presence of multiple active speakers. However, most solutions assume that the number of co-current speakers is known. Unfortunately, this information might not…
The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of filters to capture the speaker characteristics at any local…
Dynamic convolution learns a linear mixture of n static kernels weighted with their input-dependent attentions, demonstrating superior performance than normal convolution. However, it increases the number of convolutional parameters by n…
A new type of End-to-End system for text-dependent speaker verification is presented in this paper. Previously, using the phonetically discriminative/speaker discriminative DNNs as feature extractors for speaker verification has shown…
In this paper, a novel Convolutional Neural Network architecture has been developed for speaker verification in order to simultaneously capture and discard speaker and non-speaker information, respectively. In training phase, the network is…
The state-of-the-art CNN models give good performance on sentence classification tasks. The purpose of this work is to empirically study desirable properties such as semantic coherence, attention mechanism and reusability of CNNs in these…
Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…
We propose SpeakerNet - a new neural architecture for speaker recognition and speaker verification tasks. It is composed of residual blocks with 1D depth-wise separable convolutions, batch-normalization, and ReLU layers. This architecture…
Convolutional neural network (CNN) modules are widely being used to build high-end speech enhancement neural models. However, the feature extraction power of vanilla CNN modules has been limited by the dimensionality constraint of the…
Deep learning approaches are still not very common in the speaker verification field. We investigate the possibility of using deep residual convolutional neural network with spectrograms as an input features in the text-dependent speaker…
Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature fusion approach has been proposed to effectively capture speaker…
In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…
In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings. In contrast to the traditional approaches that build their speaker embeddings using manually hand-crafted…
Frequency dynamic convolution (FDY conv) has shown the state-of-the-art performance in sound event detection (SED) using frequency-adaptive kernels obtained by frequency-varying combination of basis kernels. However, FDY conv lacks an…
This paper introduces a convolutional recurrent network with attention for speech command recognition. Attention models are powerful tools to improve performance on natural language, image captioning and speech tasks. The proposed model…
Deep learning is progressively gaining popularity as a viable alternative to i-vectors for speaker recognition. Promising results have been recently obtained with Convolutional Neural Networks (CNNs) when fed by raw speech samples directly.…
Speaker verification aims to verify whether an input speech corresponds to the claimed speaker, and conventionally, this kind of system is deployed based on single-stream scenario, wherein the feature extractor operates in full frequency…