Related papers: Quantifying and Correlating Rhythm Formants in Spe…
The zones of quiet in pure-tone diffuse sound fields have been studied extensively in the past, both theoretically and experimentally, with the well known result of the 10\,dB attenuation extending to about a tenth of a wavelength. Recent…
Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy…
This paper proposes an efficient parameterization of the Room Transfer Function (RTF). Typically, the RTF rapidly varies with varying source and receiver positions, hence requires an impractical number of point to point measurements to…
Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…
The traditional approach to morphological inflection (the task of modifying a base word (lemma) to express grammatical categories) has been, for decades, to consider lexical entries of lemma-tag-form triples uniformly, lacking any…
Audio-Visual Segmentation (AVS) aims to generate pixel-wise segmentation maps that correlate with the auditory signals of objects. This field has seen significant progress with numerous CNN and Transformer-based methods enhancing the…
Over the past decade, various studies have addressed how speakers solve the so-called `The Paradigm Cell Filling Problem' (PCFP) \citep{ackerman2009parts} across different languages. The PCFP addresses a fundamental question in…
Fast Fourier Transform (FFT) relies on the HRV frequency-domain analysis techniques. It requires re-sampling of the inherently unevenly sampled heartbeat time-series (RR tachogram) to produce an evenly sampled time series of the heartbeat.…
To study the dynamical behaviour of the engineering and physical systems, we often need to capture their continuous behaviour, which is modeled using differential equations, and perform the frequency-domain analysis of these systems.…
Previous works in zero-shot text-to-speech (ZS-TTS) have attempted to enhance its systems by enlarging the training data through crowd-sourcing or augmenting existing speech data. However, the use of low-quality data has led to a decline in…
A deep neural network solution for time-scale modification (TSM) focused on large stretching factors is proposed, targeting environmental sounds. Traditional TSM artifacts such as transient smearing, loss of presence, and phasiness are…
A transversal study of the pitch variability of parkinsonian voices in read speech is presented. 30 patients suffering from Parkinson's disease (PD) and 32 healthy speakers were recorded while reading a text without voiceless phonemes. The…
Optical frequency combs are lightwaves composed of a large number of equidistant spectral lines. They are important for metrology, spectroscopy, communications and fundamental science. Frequency combs are most often generated by exciting…
Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e.g., /r/. We show age-and-sex normalized formant estimation outperforms cepstral representation for detection of fully rhotic vs.…
PT-symmetric optical resonators combine absorbing regions with active, amplifying regions. The latter are the source of radiation generated via spontaneous and stimulated emission, which embodies quantum noise and can result in lasing. We…
Reinforcement learning (RL) algorithms are highly sensitive to reward function specification, which remains a central challenge limiting their broad applicability. We present ARM-FM: Automated Reward Machines via Foundation Models, a…
Long Short-Term Memory (LSTM) and Transformers are two popular neural architectures used for natural language processing tasks. Theoretical results show that both are Turing-complete and can represent any context-free language (CFL).In…
Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…
While Large Audio Language Models (LALMs) achieve strong performance on short audio, they degrade on long-form inputs. This degradation is more severe in temporal awareness tasks, where temporal alignment becomes increasingly inaccurate as…
In this work, we propose a deep beamforming framework for speech enhancement in dynamic acoustic environments. The framework learns time-varying beamformer weights from noisy multichannel signals via a deep neural network, guided by a…