Groupe Acoustique de la Parole

Publications scientifiques récentes en France

Articles et ouvrages

• [hal-04852579] Label-constrained unsupervised domain adaptation for semantic segmentation with diffusion models
  20 décembre 2024
  Unsupervised Domain Adaptation (UDA) methods have emerged as a promising solution to generalize a learning to close datasets (domains) without the need to produce new ground truth. Nonetheless in biomedical images, some high domain shifts between source and target images […]
• [hal-04851130] Consonant lengthening marks the beginning of words across a diverse sample of languages
  20 décembre 2024
  Speech consists of a continuous stream of acoustic signals, yet humans can segment words and other constituents from each other with astonishing precision. The acoustic properties that support this process are not well understood and remain understudied for the vast […]
• [hal-04842391] C'era una svolta
  20 décembre 2024
  C'era una svoltaL'engagement politique de Luigi Nono, marqué par son militantisme au sein du Parti communiste italien, dont il est membre de 1952 à sa mort, et par ses lectures, surévaluées, de Marx, Lénine et Gramsci, avant celles de penseurs […]
• [hal-04850040] Acoustic and perceptual profiles of american english social affective expressions
  19 décembre 2024
  This pilot study reports on acoustic and perceptual profiles of two American female speakers’ productions of six American English social affective expressions: Authority, Declaration, Irritation, Sincerity, Uncertainty and walking on eggs as spoken in the linguistic sentence frame, Mary was […]

Thèses en ligne

• [tel-04828492] Amélioration Des Techniques De Conversion Vocale Appliquées à La Voix Laryngée et à La Voix Pathologique
  10 décembre 2024
  La conversion vocale (VC) vise à transformer un signal de parole émis par un locuteur source afin qu’il paraisse prononcé par un autre locuteur, appelé locuteur cible. Les systèmes de conversion vocale s’appuient généralement sur des données parallèles, où les […]
• [tel-04793473] Cracking the code of crying babies: how adults learn to understand the baby's pain
  20 novembre 2024
  Babies crying is an essential signal to elicit care, conveying both information on the baby’s identity and current physiological state (discomfort, hunger or pain). The aim of my thesis is to investigate how adults perceive information contained in babies cries, […]
• [tel-04757483] Design of a MEMS microphone based on a new device architecture
  29 octobre 2024
  In recent years, MEMS (micro-electromechanical system) microphones have become a key component in a wide range of consumer electronic devices. The need to improve upon existing applications, such as voice pickup for phone calls, as well as the development of […]
• [tel-04218098] Anonymizing Speech : Evaluating and Designing Speaker Anonymization Techniques
  14 mai 2024
  The growing use of voice user interfaces, from telephones to remote controls, automobiles, and digital assistants, has led to a surge in the collection and storage of speech data. While data collection allows for the development of efficient tools powering […]