Related papers: DUAP: Dual-task Universal Adversarial Perturbation…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Voice Authentication (VA), also known as Automatic Speaker Verification (ASV), is a widely adopted authentication method, particularly in automated systems like banking services, where it serves as a secondary layer of user authentication.…

As automatic speech recognition (ASR) systems are now being widely deployed in the wild, the increasing threat of adversarial attacks raises serious questions about the security and reliability of using such systems. On the other hand,…

Automatic speaker verification (ASV) systems use a playback detector to filter out playback attacks and ensure verification reliability. Since current playback detection models are almost always trained using genuine and played-back speech,…

This study addresses the problem of unsupervised subword unit discovery from untranscribed speech. It forms the basis of the ultimate goal of ZeroSpeech 2019, building text-to-speech systems without text labels. In this work, unit discovery…

As automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, they are typically used in conjunction with spoofing countermeasure (CM) systems to improve security. For example, the CM can first determine whether the…

Utilizing air-traffic control (ATC) data for downstream natural-language processing tasks requires preprocessing steps. Key steps are the transcription of the data via automatic speech recognition (ASR) and speaker diarization, respectively…

Deep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO). However, their susceptibility to adversarial examples poses a critical challenge, compromising the reliability…

Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of…

Adversarial examples seem to be inevitable. These specifically crafted inputs allow attackers to arbitrarily manipulate machine learning systems. Even worse, they often seem harmless to human observers. In our digital society, this poses a…

Voice biometric systems based on automatic speaker verification (ASV) are exposed to \textit{spoofing} attacks which may compromise their security. To increase the robustness against such attacks, anti-spoofing or presentation attack…

Security of automatic speaker verification (ASV) systems is compromised by various spoofing attacks. While many types of non-proactive attacks (and their defenses) have been studied in the past, attacker's perspective on ASV, represents a…

Speech enabled foundation models, either in the form of flexible speech recognition based systems or audio-prompted large language models (LLMs), are becoming increasingly popular. One of the interesting aspects of these models is their…

Despite the recent advancement in speech emotion recognition (SER) within a single corpus setting, the performance of these SER systems degrades significantly for cross-corpus and cross-language scenarios. The key reason is the lack of…

In a modern vehicle, there are over seventy Electronics Control Units (ECUs). For an in-vehicle network, ECUs communicate with each other by following a standard communication protocol, such as Controller Area Network (CAN). However, an…

Anomalous sound detection for machine condition monitoring has great potential in the development of Industry 4.0. However, these anomalous sounds of machines are usually unavailable in normal conditions. Therefore, the models employed have…

CAPTCHAs are designed to prevent malicious bot programs from abusing websites. Most online service providers deploy audio CAPTCHAs as an alternative to text and image CAPTCHAs for visually impaired users. However, prior research…

Adversarial detection is designed to identify and reject maliciously crafted adversarial examples(AEs) which are generated to disrupt the classification of target models. Presently, various input transformation-based methods have been…

We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based…

Speech and speaker recognition systems are employed in a variety of applications, from personal assistants to telephony surveillance and biometric authentication. The wide deployment of these systems has been made possible by the improved…