相关论文: Transport-Oriented Feature Aggregation for Speaker…

Self-supervised learning of speech representations from large amounts of unlabeled data has enabled state-of-the-art results in several speech processing tasks. Aggregating these speech representations across time is typically approached by…

Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network. The pooling layer in the network aims to aggregate frame-level features extracted by the backbone. In this paper, we propose a…

Over the recent years, various deep learning-based embedding methods have been proposed and have shown impressive performance in speaker verification. However, as in most of the classical embedding techniques, the deep learning-based…

This paper presents an experimental study on deep speaker embedding with an attention mechanism that has been found to be a powerful representation learning technique in speaker recognition. In this framework, an attention model works as a…

In conventional deep speaker embedding frameworks, the pooling layer aggregates all frame-level features over time and computes their mean and standard deviation statistics as inputs to subsequent segment-level layers. Such statistics…

Current speaker verification techniques rely on a neural network to extract speaker representations. The successful x-vector architecture is a Time Delay Neural Network (TDNN) that applies statistics pooling to project variable-length…

Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was…

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…

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

The goal of this paper is to adapt speaker embeddings for solving the problem of speaker diarisation. The quality of speaker embeddings is paramount to the performance of speaker diarisation systems. Despite this, prior works in the field…

Deep speaker embeddings have become the leading method for encoding speaker identity in speaker recognition tasks. The embedding space should ideally capture the variations between all possible speakers, encoding the multiple acoustic…

Verifying the identity of a speaker is crucial in modern human-machine interfaces, e.g., to ensure privacy protection or to enable biometric authentication. Classical speaker verification (SV) approaches estimate a fixed-dimensional…

Single channel target speaker separation (TSS) aims at extracting a speaker's voice from a mixture of multiple talkers given an enrollment utterance of that speaker. A typical deep learning TSS framework consists of an upstream model that…

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into…

This paper presents a streaming extension for the Sortformer speaker diarization framework, whose key property is the arrival-time ordering of output speakers. The proposed approach employs an Arrival-Order Speaker Cache (AOSC) to store…

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…

With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto approach. However, the pooling problem remains; the length of…

The paper presents a novel approach to refining similarity scores between input utterances for robust speaker verification. Given the embeddings from a pair of input utterances, a graph model is designed to incorporate additional…

In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for adapting those pre-trained models to speaker verification…

Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully…