English
Related papers

Related papers: Muting Whisper: A Universal Acoustic Adversarial A…

200 papers

In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to…

Sound · Computer Science 2024-05-31 Bandhav Veluri , Malek Itani , Tuochao Chen , Takuya Yoshioka , Shyamnath Gollakota

Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-19 Arindam Jati , Chin-Cheng Hsu , Monisankha Pal , Raghuveer Peri , Wael AbdAlmageed , Shrikanth Narayanan

Automatic speech recognition (ASR) systems are ubiquitously present in our daily devices. They are vulnerable to adversarial attacks, where manipulated input samples fool the ASR system's recognition. While adversarial examples for various…

Computation and Language · Computer Science 2022-02-03 Karla Markert , Donika Mirdita , Konstantin Böttinger

We propose using a computational model of the auditory cortex as a defense against adversarial attacks on audio. We apply several white-box iterative optimization-based adversarial attacks to an implementation of Amazon Alexa's HW network,…

Sound · Computer Science 2021-11-18 Ilya Kavalerov , Ruijie Zheng , Wojciech Czaja , Rama Chellappa

Although end-to-end automatic speech recognition (e2e ASR) models are widely deployed in many applications, there have been very few studies to understand models' robustness against adversarial perturbations. In this paper, we explore…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-08 Zhiyun Lu , Wei Han , Yu Zhang , Liangliang Cao

Modern zero-shot text-to-speech (TTS) models offer unprecedented expressivity but also pose serious crime risks, as they can synthesize voices of individuals who never consented. In this context, speaker unlearning aims to prevent the…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-29 Myungjin Lee , Eunji Shin , Jiyoung Lee

We present an approach to synthesize whisper by applying a handcrafted signal processing recipe and Voice Conversion (VC) techniques to convert normally phonated speech to whispered speech. We investigate using Gaussian Mixture Models (GMM)…

Adversarial machine learning research has recently demonstrated the feasibility to confuse automatic speech recognition (ASR) models by introducing acoustically imperceptible perturbations to audio samples. To help researchers and…

Machine Learning · Computer Science 2018-05-31 Nilaksh Das , Madhuri Shanbhogue , Shang-Tse Chen , Li Chen , Michael E. Kounavis , Duen Horng Chau

In many speech-enabled human-machine interaction scenarios, user speech can overlap with the device playback audio. In these instances, the performance of tasks such as keyword-spotting (KWS) and device-directed speech detection (DDD) can…

Sound · Computer Science 2022-10-05 Samuele Cornell , Thomas Balestri , Thibaud Sénéchal

Speech synthesis technology has brought great convenience, while the widespread usage of realistic deepfake audio has triggered hazards. Malicious adversaries may unauthorizedly collect victims' speeches and clone a similar voice for…

Sound · Computer Science 2025-04-15 Zhisheng Zhang , Derui Wang , Qianyi Yang , Pengyang Huang , Junhan Pu , Yuxin Cao , Kai Ye , Jie Hao , Yixian Yang

It is now well-known that automatic speaker verification (ASV) systems can be spoofed using various types of adversaries. The usual approach to counteract ASV systems against such attacks is to develop a separate spoofing countermeasure…

Cryptography and Security · Computer Science 2024-01-30 Xuechen Liu , Md Sahidullah , Kong Aik Lee , Tomi Kinnunen

Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-16 Tejas Jayashankar , Jonathan Le Roux , Pierre Moulin

Despite the strong performance of current NLP models, they can be brittle against adversarial attacks. To enable effective learning against adversarial inputs, we introduce the use of rationale models that can explicitly learn to ignore…

Computation and Language · Computer Science 2023-02-22 Yiming Zhang , Yangqiaoyu Zhou , Samuel Carton , Chenhao Tan

Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this lengthy reasoning process incurs substantial computational and latency overheads, hindering the…

Computation and Language · Computer Science 2026-05-19 Heming Xia , Cunxiao Du , Rui Li , Chak Tou Leong , Yongqi Li , Wenjie Li

The field of audio captioning has seen significant advancements in recent years, driven by the availability of large-scale audio datasets and advancements in deep learning techniques. In this technical report, we present our approach to…

Sound · Computer Science 2023-05-18 Marek Kadlčík , Adam Hájek , Jürgen Kieslich , Radosław Winiecki

Automatic speech recognition (ASR) systems are vulnerable to audio adversarial examples that attempt to deceive ASR systems by adding perturbations to benign speech signals. Although an adversarial example and the original benign wave are…

Cryptography and Security · Computer Science 2021-12-14 Namgyu Park , Sangwoo Ji , Jong Kim

Automated speech recognition (ASR) models have gained prominence for applications such as captioning, speech translation, and live transcription. This paper studies Whisper and two model variants: one optimized for live speech streaming and…

Sound · Computer Science 2025-03-14 Allison Andreyev

Audio-native large language models (audio-LLMs) commonly use Whisper as their audio encoder. However, Whisper was trained exclusively on speech data, producing weak representations for music and environmental sound. This forces downstream…

In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers…

Computation and Language · Computer Science 2019-06-27 Naoyuki Kanda , Shota Horiguchi , Ryoichi Takashima , Yusuke Fujita , Kenji Nagamatsu , Shinji Watanabe

Speech synthesis systems can now produce highly realistic vocalisations that pose significant authenticity challenges. Despite substantial progress in deepfake detection models, their real-world effectiveness is often undermined by evolving…

Sound · Computer Science 2026-02-12 Qizhou Wang , Hanxun Huang , Guansong Pang , Sarah Erfani , Christopher Leckie
‹ Prev 1 8 9 10 Next ›