相关论文: Improving Membership Inference in ASR Model Auditi…

Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive…

Automatic Speech Recognition (ASR) is widely used within consumer devices such as mobile phones. Recently, personalization or on-device model fine-tuning has shown that adaptation of ASR models towards target user speech improves their…

Automatic speech recognition (ASR) on multi-talker recordings is challenging. Current methods using 3D spatial data from multi-channel audio and visual cues focus mainly on direct waves from the target speaker, overlooking reflection wave…

Membership Inference Attacks (MIAs) pose a significant privacy risk by enabling adversaries to determine if a specific data point was part of a model's training set. This work empirically investigates whether MU algorithms can function as a…

Machine learning systems can produce personalized outputs that allow an adversary to infer sensitive input attributes at inference time. We introduce Robust Privacy (RP), an inference-time privacy notion inspired by certified robustness: if…

Our prior experiments show that humans and machines seem to employ different approaches to speaker discrimination, especially in the presence of speaking style variability. The experiments examined read versus conversational speech.…

Currently, Automatic Speech Recognition (ASR) models are deployed in an extensive range of applications. However, recent studies have demonstrated the possibility of adversarial attack on these models which could potentially suppress or…

Automatic Speech Recognition (ASR) systems suffer considerably when source speech is corrupted with noise or room impulse responses (RIR). Typically, speech enhancement is applied in both mismatched and matched scenario training and…

This article introduces the Membership Inference Test (MINT), a novel approach that aims to empirically assess if given data was used during the training of AI/ML models. Specifically, we propose two MINT architectures designed to learn the…

Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise or reverberation. However, such speech enhancement techniques…

Speech emotion recognition (SER) processes speech signals to detect and characterize expressed perceived emotions. Many SER application systems often acquire and transmit speech data collected at the client-side to remote cloud platforms…

Non-intrusive intelligibility prediction is important for its application in realistic scenarios, where a clean reference signal is difficult to access. The construction of many non-intrusive predictors require either ground truth…

As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used during training, despite growing concerns about their…

Automatic speech recognition (ASR) has witnessed remarkable progress in recent years, largely driven by the emergence of LLM-based ASR paradigm. Despite their strong performance on a variety of open-source benchmarks, existing LLM-based ASR…

Researchers have demonstrated that Automatic Speech Recognition (ASR) systems perform differently across demographic groups. In this work, we examined how subtitle errors affect evaluations of speakers and their content using a…

An automatic speech recognition (ASR) system based on a deep neural network is vulnerable to attack by an adversarial example, especially if the command-dependent ASR fails. A defense method against adversarial examples is proposed to…

Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with several immediate…

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the…

We propose a novel and practical privacy notion called $f$-Membership Inference Privacy ($f$-MIP), which explicitly considers the capabilities of realistic adversaries under the membership inference attack threat model. Consequently,…

Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In…