相关论文: WavShape: Information-Theoretic Speech Representat…

Automatic recognition of disordered speech remains a highly challenging task to date. Sources of variability commonly found in normal speech including accent, age or gender, when further compounded with the underlying causes of speech…

In this article, we propose a new variational approach to learn private and/or fair representations. This approach is based on the Lagrangians of a new formulation of the privacy and fairness optimization problems that we propose. In this…

Recently, speaker embeddings extracted from a speaker discriminative deep neural network (DNN) yield better performance than the conventional methods such as i-vector. In most cases, the DNN speaker classifier is trained using cross entropy…

Recent studies have introduced methods for learning acoustic word embeddings (AWEs)---fixed-size vector representations of words which encode their acoustic features. Despite the widespread use of AWEs in speech processing research, they…

A general disentanglement-based speaker anonymization system typically separates speech into content, speaker, and prosody features using individual encoders. This paper explores how to adapt such a system when a new speech attribute, for…

In the era of big data, remarkable advancements have been achieved in personalized speech generation techniques that utilize speaker attributes, including voice and speaking style, to generate deepfake speech. This has also amplified global…

This paper proposes a unified deep speaker embedding framework for modeling speech data with different sampling rates. Considering the narrowband spectrogram as a sub-image of the wideband spectrogram, we tackle the joint modeling problem…

Text embedding inversion attacks reconstruct original sentences from latent representations, posing severe privacy threats in collaborative inference and edge computing. We propose TextCrafter, an optimization-based adversarial perturbation…

Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…

Self-supervised representation learning for speech often involves a quantization step that transforms the acoustic input into discrete units. However, it remains unclear how to characterize the relationship between these discrete units and…

Non-intrusive speech intelligibility prediction remains challenging due to variability in speakers, noise conditions, and subjective perception. We propose an uncertainty-aware approach that leverages Whisper embeddings in combination with…

Overlapping speech diarization is always treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set. Specifically, we…

Deep speaker embeddings have been shown effective for assessing cognitive impairments aside from their original purpose of speaker verification. However, the research found that speaker embeddings encode speaker identity and an array of…

The widespread adoption of voice-enabled authentication and audio biometric systems have significantly increased privacy vulnerabilities associated with sensitive speech data. Compliance with privacy regulations such as GDPR's right to be…

Speaker diarization, the process of segmenting an audio stream or transcribed speech content into homogenous partitions based on speaker identity, plays a crucial role in the interpretation and analysis of human speech. Most existing…

Whisper has become the de-facto encoder for extracting general-purpose audio features in large audio-language models, where a 30-second clip is typically represented by 1500 frame features projected into an LLM. In contrast, audio-text…

Speech watermarking techniques can proactively mitigate the potential harmful consequences of instant voice cloning techniques. These techniques involve the insertion of signals into speech that are imperceptible to humans but can be…

Disentanglement-based speaker anonymization involves decomposing speech into a semantically meaningful representation, altering the speaker embedding, and resynthesizing a waveform using a neural vocoder. State-of-the-art systems of this…

Large-scale end-to-end models such as Whisper have shown strong performance on diverse speech tasks, but their internal behavior on pathological speech remains poorly understood. Understanding how dysarthric speech is represented across…

Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts…