Related papers: An Invertible Discrete Auditory Transform
Voice anonymization masks vocal traits while preserving linguistic content, which may still leak speaker-specific patterns. To assess and strengthen privacy evaluation, we propose a dual-stream attacker that fuses spectral and…
The fundamental diversity-multiplexing tradeoff (DMT) of the quasi-static fading, symmetric $2$-user MIMO interference channel (IC) with channel state information at the transmitters (CSIT) and a short term average power constraint is…
Bootstrap-based Self-Supervised Learning (SSL) has achieved remarkable progress in audio understanding. However, existing methods typically operate at a single level of granularity, limiting their ability to model the diverse temporal and…
Dysarthric speech reconstruction (DSR) systems aim to automatically convert dysarthric speech into normal-sounding speech. The technology eases communication with speakers affected by the neuromotor disorder and enhances their social…
We measure the shot noise of a quantum point-contact using a capacitively coupled InAs double quantum dot as an on-chip sensor. Our measurement signals are the (bidirectional) interdot electronic tunneling rates which are determined by…
An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker,…
The intrinsic limitation of the material nonlinearity inevitably results in the poor mode purity, conversion efficiency and real-time reconfigurability of the generated harmonic waves, both in optics and acoustics. Rotational Doppler effect…
Distributed Acoustic Sensing (DAS) is a promising technology introducing a new paradigm in the acquisition of high-resolution seismic data. However, DAS data often show weak signals compared to the background noise, especially in tough…
FM Synthesis is a well-known algorithm used to generate complex timbre from a compact set of design primitives. Typically featuring a MIDI interface, it is usually impractical to control it from an audio source. On the other hand,…
We answer the question in the title, showing that adversarial training (AT) for diffusion models (DMs) fundamentally differs from classifiers: while AT in classifiers enforces output invariance, AT in DMs requires equivariance to keep the…
Signal-dependent beamformers are advantageous over signal-independent beamformers when the acoustic scenario - be it real-world or simulated - is straightforward in terms of the number of sound sources, the ambient sound field and their…
To improve speech intelligibility in complex everyday situations, the human auditory system partially relies on Interaural Time Differences (ITDs) and Interaural Level Differences (ILDs). However, hearing impaired (HI) listeners often…
A tabletop low-noise differential amplifer with a bandwidth of 100 kHz is presented. Low voltage drifts of the order of 100 nV/day are reached by thermally stabilizing relevant amplifer components. The input leakage current is below 100 fA.…
Transformers have emerged as a prominent model framework for audio tagging (AT), boasting state-of-the-art (SOTA) performance on the widely-used Audioset dataset. However, their impressive performance often comes at the cost of high memory…
The utility of inertial sensors depends on resilience against real-world dynamics and noise. Atom interferometry offers a sensing technology with the advantage of good long-term stability, high sensitivity, and accuracy. High measurement…
From customer feedback to social media, understanding human sentiment in text is central to how machines can interact meaningfully with people. However, despite notable progress, accurately capturing sentiment remains a challenging task,…
We consider the problem of computing the Walsh-Hadamard Transform (WHT) of some $N$-length input vector in the presence of noise, where the $N$-point Walsh spectrum is $K$-sparse with $K = {O}(N^{\delta})$ scaling sub-linearly in the input…
Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…
Curriculum learning begins to thrive in the speech enhancement area, which decouples the original spectrum estimation task into multiple easier sub-tasks to achieve better performance. Motivated by that, we propose a dual-branch…
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…