相关论文: Challenging margin-based speaker embedding extract…

In this paper, we propose a noise robust bottleneck feature representation which is generated by an adversarial network (AN). The AN includes two cascade connected networks, an encoding network (EN) and a discriminative network (DN).…

Data augmentation (DA) has gained widespread popularity in deep speaker models due to its ease of implementation and significant effectiveness. It enriches training data by simulating real-life acoustic variations, enabling deep neural…

Automatic Speaker Verification (ASV) suffers from performance degradation in noisy conditions. To address this issue, we propose a novel adversarial learning framework that incorporates noise-disentanglement to establish a noise-independent…

Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. However, the sequential text generation common pitfall with VAEs is that the model tends to ignore latent variables with a strong auto-regressive…

Recent advancements in adversarial attacks have demonstrated their effectiveness in misleading speaker recognition models, making wrong predictions about speaker identities. On the other hand, defense techniques against speaker-adversarial…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

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…

Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to…

This paper investigates task-oriented communication for edge inference, where a low-end edge device transmits the extracted feature vector of a local data sample to a powerful edge server for processing. It is critical to encode the data…

We analyze the impact of speaker adaptation in end-to-end automatic speech recognition models based on transformers and wav2vec 2.0 under different noise conditions. By including speaker embeddings obtained from x-vector and ECAPA-TDNN…

This paper presents a robust multi-channel speaker extraction algorithm designed to handle inaccuracies in reference information. While existing approaches often rely solely on either spatial or spectral cues to identify the target speaker,…

We propose an end-to-end speaker verification system based on the neural network and trained by a loss function with less computational complexity. The end-to-end speaker verification system in this paper consists of a ResNet architecture…

Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD)…

There has been great interest in enhancing the robustness of neural network classifiers to defend against adversarial perturbations through adversarial training, while balancing the trade-off between robust accuracy and standard accuracy.…

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity…

Large Language Models (LLMs) excel at various tasks, including solving math word problems (MWPs), but struggle with real-world problems containing irrelevant information. To address this, we propose a prompting framework that generates…

The state-of-the-art approach for semi-supervised anomalous sound detection is to first learn an embedding space by using auxiliary classification tasks based on meta information or self-supervised learning and then estimate the…

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…

Studies have shown that in noisy acoustic environments, providing binaural signals to the user of an assistive listening device may improve speech intelligibility and spatial awareness. This paper presents a binaural speech enhancement…

In this paper we introduce a recurrent neural network (RNN) based variational autoencoder (VAE) model with a new constrained loss function that can generate more meaningful electroencephalography (EEG) features from raw EEG features to…