相关论文: Interpreting Multi-Branch Anti-Spoofing Architectu…

Automatic Speech Recognition (ASR) is an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibility tools. Yet ASR systems continue to struggle with the…

Unsupervised domain adaptation of speech signal aims at adapting a well-trained source-domain acoustic model to the unlabeled data from target domain. This can be achieved by adversarial training of deep neural network (DNN) acoustic models…

This paper describes our proposed integration system for the spoofing-aware speaker verification challenge. It consists of a robust spoofing-aware verification system that use the speaker verification and antispoofing embeddings extracted…

Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion, its performance scales poorly with dataset complexity. On…

Self-supervised Audio Transformers (SAT) enable great success in many downstream speech applications like ASR, but how they work has not been widely explored yet. In this work, we present multiple strategies for the analysis of attention…

Semi-supervised learning (SSL) has shown considerable potential in medical image segmentation, primarily leveraging consistency regularization and pseudo-labeling. However, many SSL approaches only pay attention to low-level consistency and…

In this paper, we present our comprehensive study aimed at enhancing the generalization capabilities of audio deepfake detection models. We investigate the performance of various pre-trained backbones, including Wav2Vec2, WavLM, and…

Lately, the self-attention mechanism has marked a new milestone in the field of automatic speech recognition (ASR). Nevertheless, its performance is susceptible to environmental intrusions as the system predicts the next output symbol…

In stereo vision, self-similar or bland regions can make it difficult to match patches between two images. Active stereo-based methods mitigate this problem by projecting a pseudo-random pattern on the scene so that each patch of an image…

Fooling deep neural networks with adversarial input have exposed a significant vulnerability in the current state-of-the-art systems in multiple domains. Both black-box and white-box approaches have been used to either replicate the model…

Active subspace is a model reduction method widely used in the uncertainty quantification community. In this paper, we propose analyzing the internal structure and vulnerability and deep neural networks using active subspace. Firstly, we…

The automatic speaker verification spoofing and countermeasures (ASVspoof) challenge series is a community-led initiative which aims to promote the consideration of spoofing and the development of countermeasures. ASVspoof 2021 is the 4th…

In this paper we investigate the use of adversarial domain adaptation for addressing the problem of language mismatch between speaker recognition corpora. In the context of speaker verification, adversarial domain adaptation methods aim at…

Audio deepfake detection has become a pivotal task over the last couple of years, as many recent speech synthesis and voice cloning systems generate highly realistic speech samples, thus enabling their use in malicious activities. In this…

Monaural multi-speaker automatic speech recognition (ASR) remains challenging due to data scarcity and the intrinsic difficulty of recognizing and attributing words to individual speakers, particularly in overlapping speech. Recent advances…

Automatic speech recognition and voice identification systems are being deployed in a wide array of applications, from providing control mechanisms to devices lacking traditional interfaces, to the automatic transcription of conversations…

The spoof speech detection (SSD) is the essential countermeasure for automatic speaker verification systems. Although SSD with magnitude features in the frequency domain has shown promising results, the phase information also can be…

The integration of Artificial Intelligence (AI) in education requires scalable and efficient frameworks that balance performance, adaptability, and cost. This paper addresses these needs by proposing a shared backbone model architecture…

The current automatic speaker verification (ASV) task involves making binary decisions on two types of trials: target and non-target. However, emerging advancements in speech generation technology pose significant threats to the reliability…

Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of…