Related papers: Spatial Pyramid Encoding with Convex Length Normal…

This paper aims to improve the widely used deep speaker embedding x-vector model. We propose the following improvements: (1) a hybrid neural network structure using both time delay neural network (TDNN) and long short-term memory neural…

Personalized speech enhancement (PSE) models can improve the audio quality of teleconferencing systems by adapting to the characteristics of a speaker's voice. However, most existing methods require a separate speaker embedding model to…

We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including…

This paper presents an end-to-end text-independent speaker verification framework by jointly considering the speaker embedding (SE) network and automatic speech recognition (ASR) network. The SE network learns to output an embedding vector…

The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. On the other…

Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a…

In speaker verification, the extraction of voice representations is mainly based on the Residual Neural Network (ResNet) architecture. ResNet is built upon convolution layers which learn filters to capture local spatial patterns along all…

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…

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

This paper proposes a novel Sequence-to-Sequence Neural Diarization (S2SND) framework to perform online and offline speaker diarization. It is developed from the sequence-to-sequence architecture of our previous target-speaker voice…

In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…

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…

We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple…

This paper proposes attentive statistics pooling for deep speaker embedding in text-independent speaker verification. In conventional speaker embedding, frame-level features are averaged over all the frames of a single utterance to form an…

The classical i-vectors and the latest end-to-end deep speaker embeddings are the two representative categories of utterance-level representations in automatic speaker verification systems. Traditionally, once i-vectors or deep speaker…

Speaker embeddings extracted with deep 2D convolutional neural networks are typically modeled as projections of first and second order statistics of channel-frequency pairs onto a linear layer, using either average or attentive pooling…

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persistent challenge. In this paper, we propose a novel self-supervised speaker verification approach, Self-Distillation…

Self-supervised speech representations are known to encode both speaker and phonetic information, but how they are distributed in the high-dimensional space remains largely unexplored. We hypothesize that they are encoded in orthogonal…

Separating different speaker properties from a multi-speaker environment is challenging. Instead of separating a two-speaker signal in signal space like speech source separation, a speaker embedding de-mixing approach is proposed. The…

Personalized speech enhancement (PSE) methods typically rely on pre-trained speaker verification models or self-designed speaker encoders to extract target speaker clues, guiding the PSE model in isolating the desired speech. However, these…