Related papers: Graph Attention Networks for Speaker Verification

Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full…

Speaker embeddings achieve promising results on many speaker verification tasks. Phonetic information, as an important component of speech, is rarely considered in the extraction of speaker embeddings. In this paper, we introduce phonetic…

Recent studies have shown that frame-level deep speaker features can be derived from a deep neural network with the training target set to discriminate speakers by a short speech segment. By pooling the frame-level features, utterance-level…

Speaker embeddings represent a means to extract representative vectorial representations from a speech signal such that the representation pertains to the speaker identity alone. The embeddings are commonly used to classify and discriminate…

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…

In this paper, we analyze the behavior and performance of speaker embeddings and the back-end scoring model under domain and language mismatch. We present our findings regarding ResNet-based speaker embedding architectures and show that…

Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation. In this paper, we propose an end-to-end ASD workflow where feature learning and…

Even though deep speaker models have demonstrated impressive accuracy in speaker verification tasks, this often comes at the expense of increased model size and computation time, presenting challenges for deployment in resource-constrained…

We present path2vec, a new approach for learning graph embeddings that relies on structural measures of pairwise node similarities. The model learns representations for nodes in a dense space that approximate a given user-defined graph…

The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions.…

This paper proposes a multi-task learning network with phoneme-aware and channel-wise attentive learning strategies for text-dependent Speaker Verification (SV). In the proposed structure, the frame-level multi-task learning along with the…

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…

In this article we propose a novel approach for adapting speaker embeddings to new domains based on adversarial training of neural networks. We apply our embeddings to the task of text-independent speaker verification, a challenging,…

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…

We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional countermeasure embeddings, which lack interpretability, the proposed…

Modeling the rich prosodic variations inherent in human speech is essential for generating natural-sounding speech. While speaker embeddings are commonly used as conditioning inputs in personalized speech generation, they are typically…

Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling. Given the success of statistics-based pooling methods, we hypothesize that speaker characteristics are well represented in the…

Artefacts that serve to distinguish bona fide speech from spoofed or deepfake speech are known to reside in specific subbands and temporal segments. Various approaches can be used to capture and model such artefacts, however, none works…

In this study, we explore the potential of visibility graphs in the spectral domain for speaker recognition. Adult participants were instructed to record vocalizations of the five Spanish vowels. For each vocalization, we computed the…

State-of-the-art audio captioning methods typically use the encoder-decoder structure with pretrained audio neural networks (PANNs) as encoders for feature extraction. However, the convolution operation used in PANNs is limited in capturing…