Related papers: CallShield: Secure Caller Authentication over Real…

Voice biometrics is drawing increasing attention as it is a promising alternative to legacy passwords for user authentication. Recently, a growing body of work shows that voice biometrics is vulnerable to spoofing through replay attacks,…

In the realm of audio watermarking, it is challenging to simultaneously encode imperceptible messages while enhancing the message capacity and robustness. Although recent advancements in deep learning-based methods bolster the message…

Audio fingerprinting techniques have seen great advances in recent years, enabling accurate and fast audio retrieval even in conditions when the queried audio sample has been highly deteriorated or recorded in noisy conditions. Expectedly,…

Speech provenance goes beyond detecting whether a watermark is present. Real workflows involve splicing, quoting, trimming, and platform-level transforms that may preserve some regions while altering others. Neural watermarking systems have…

Receiving calls is one of the most universal functions of smartphones, involving sensitive information and critical operations. Unfortunately, to prioritize convenience, the current call receiving process bypasses smartphone authentication…

This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…

Voice input has been tremendously improving the user experience of mobile devices by freeing our hands from typing on the small screen. Speech recognition is the key technology that powers voice input, and it is usually outsourced to the…

We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully…

The rise of AI voice-cloning technology, particularly audio Real-time Deepfakes (RTDFs), has intensified social engineering attacks by enabling real-time voice impersonation that bypasses conventional enrollment-based authentication. This…

Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities. However, existing techniques do not scale efficiently, especially while handling long form streaming audio inputs…

Voice cloning (VC)-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by training them on watermarked audio but fail in zero-shot VC…

Audio watermarking embeds auxiliary information into speech while maintaining speaker identity, linguistic content, and perceptual quality. Although recent advances in neural and digital signal processing-based watermarking methods have…

Audio watermarking is widely used for leaking source tracing. The robustness of the watermark determines the traceability of the algorithm. With the development of digital technology, audio re-recording (AR) has become an efficient and…

Wireless networks are vulnerable to jamming attacks due to the shared communication medium, which can severely degrade performance and disrupt services. Despite extensive research, current jamming detection methods often rely on simulated…

We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adapt offline models through chunking or sliding windows,…

We introduce Speech ReaLLM, a new ASR architecture that marries "decoder-only" ASR with the RNN-T to make multimodal LLM architectures capable of real-time streaming. This is the first "decoder-only" ASR architecture designed to handle…

Recent works show that speech separation guided diarization (SSGD) is an increasingly promising direction, mainly thanks to the recent progress in speech separation. It performs diarization by first separating the speakers and then applying…

As deep learning advances in audio generation, challenges in audio security and copyright protection highlight the need for robust audio watermarking. Recent neural network-based methods have made progress but still face three main issues:…

The widespread use of earphones has enabled various sensing applications, including activity recognition, health monitoring, and context-aware computing. Among these, earphone-based user authentication has become a key technique by…

In this article, the authors discuss the problem of forensic authentication of digital audio recordings. Although forensic audio has been addressed in several articles, the existing approaches are focused on analog magnetic recordings,…