arXiv subjects

Pablo Pérez Zarazaga

Publications and source records attributed to Pablo Pérez Zarazaga.

4 recordsLinked to original sources

arXiv2026

HiFi-Glot: High-Fidelity Neural Formant Synthesis with Differentiable Resonant Filters

Formant synthesis aims to generate speech with controllable formant structures, enabling precise control of vocal resonance and phonetic features. However, while existing formant synthesis approaches enable precise formant manipulation, they often yield an impoverished speech signal by failing to capture the complex co-occurring acoustic cues essential for naturalness. To address this issue, this letter presents HiFi-Glot, an end-to-end neural formant synthesis system that achieves both precise formant control and high-fidelity speech synthesis. Specifically, the proposed model adopts a source--filter architecture inspired by classical formant synthesis, where a neural vocoder generates the glottal excitation signal, and differentiable resonant filters model the formants to produce the speech waveform. Experiment results demonstrate that our proposed HiFi-Glot model can generate speech with higher perceptual quality and naturalness while exhibiting a more precise control over formant frequencies, outperforming industry-standard formant manipulation tools such as Praat. Code, checkpoints, and representative audio samples are available at https://www.yichenggu.com/HiFi-Glot/.

cs.SD↗

arXiv2023

Recovering implicit pitch contours from formants in whispered speech

Whispered speech is characterised by a noise-like excitation that results in the lack of fundamental frequency. Considering that prosodic phenomena such as intonation are perceived through f0 variation, the perception of whispered prosody is relatively difficult. At the same time, studies have shown that speakers do attempt to produce intonation when whispering and that prosodic variability is being transmitted, suggesting that intonation "survives" in whispered formant structure. In this paper, we aim to estimate the way in which formant contours correlate with an "implicit" pitch contour in whisper, using a machine learning model. We propose a two-step method: using a parallel corpus, we first transform the whispered formants into their phonated equivalents using a denoising autoencoder. We then analyse the formant contours to predict phonated pitch contour variation. We observe that our method is effective in establishing a relationship between whispered and phonated formants and in uncovering implicit pitch contours in whisper.

eess.AS↗

arXiv2023

Speaker-independent neural formant synthesis

We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-learning advances to provide a highly realistic signal generator that includes control affordances required for stimulus creation in the speech sciences. Our approach turns input speech parameters into predicted mel-spectrograms, which are rendered into waveforms by a pre-trained neural vocoder. Experiments with WaveNet and HiFi-GAN confirm that the method achieves our goals of accurate control over speech parameters combined with high perceptual audio quality. We also find that the small set of phonetically relevant speech parameters we use is sufficient to allow for speaker-independent synthesis (a.k.a. universal vocoding).

eess.AS↗

arXiv2020

Users Perceptions about Teleconferencing Applications Collected through Twitter

The COVID-19 outbreak disrupted different organizations, employees and students, who turned to teleconference applications to collaborate and socialize even during the quarantine. Thus, the demand of teleconferencing applications surged with mobile application downloads reaching the highest number ever seen. However, some of the teleconference applications recently suffered from several issues such as security, privacy, media quality, reliability, capacity and technical difficulties. Thus, in this work, we explore the opinions of different users towards different teleconference applications. Firstly, posts on Twitter, known as tweets, about remote working and different teleconference applications are extracted using different keywords. Then, the extracted tweets are passed to sentiment classifier to classify the tweets into positive and negative. Afterwards, the most important features of different teleconference applications are extracted and analyzed. Finally, we highlight the main strengths, drawbacks and challenges of different teleconference applications.

cs.CY↗