Results 21 to 30 of about 36,891 (314)
Reconstruction of Phonated Speech from Whispers Using Formant-Derived Plausible Pitch Modulation [PDF]
, 2015 Whispering is a natural, unphonated, secondary aspect of speech communications for most people. However, it is the primary mechanism of communications for some speakers who have impaired voice production mechanisms, such as partial laryngectomees, as ...
Sharifzadeh, Hamid Reza +4 more
core +1 more source
Physical Review Letters, 2000 Experiments indicating the excitation of whispering gallery type electromagnetic modes by a vortex moving in an annular Josephson junction are reported. At relativistic velocities the Josephson vortex interacts with the modes of the superconducting stripline resonator giving rise to novel resonances on the current-voltage characteristic of the junction.
Wallraff, A. +4 more
openaire +4 more sources
Reproducing Whisper-Style Training Using An Open-Source Toolkit And Publicly Available Data [PDF]
Automatic Speech Recognition & Understanding, 2023 Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech data.
Yifan Peng +15 more
semanticscholar +1 more source
Careless Whisper: Speech-to-Text Hallucination Harms [PDF]
Conference on Fairness, Accountability and TransparencySpeech-to-text services aim to transcribe input audio as accurately as possible. They increasingly play a role in everyday life, for example in personal voice assistants or in customer-company interactions.
Allison Koenecke +4 more
semanticscholar +1 more source
Whisper-to-speech conversion using restricted Boltzmann machine arrays [PDF]
, 2014 Whispers are a natural vocal communication mechanism, in which vocal cords do not vibrate normally. Lack of glottal-induced pitch leads to low energy, and an inherent noise-like spectral distribution reduces intelligibility.
Li, Jing-jie +3 more
core +1 more source
Adaptation of Whisper models to child speech recognition [PDF]
Interspeech, 2023 Automatic Speech Recognition (ASR) systems often struggle with transcribing child speech due to the lack of large child speech datasets required to accurately train child-friendly ASR models.
Rishabh Jain +4 more
semanticscholar +1 more source
Generative AI Model For Semantic Image Construction From Audio Prompts [PDF]
ITM Web of ConferencesGenerative AI is a platform which produces many types of content. It enables users to develop images via description of them in words. Also it is a fact that most of our communication is through speech as opposed to writing. In this study we present what
H R Mithuna +6 more
doaj +1 more source
Kur’an’da Yer Alan ‘Şeytan’ın Adımlarını İzlemeyin’ İfadesinin Anlam ve Yorumu Üzerine
Cumhuriyet İlahiyat Dergisi, 2017 Kur’an’da “Lâ tettebiʿû ḫuṭuvâti’ş-şeyṭân” ifadesi dört yerde geçmektedir. İfade aynı olmasına rağmen geçtikleri bağlamları farklıdır. Bu ifadenin birbirinden farklı bağlamlarda geçiyor olması bu farklı bağlamların ortak bir noktasının olmasını ...
Muhammed Ersöz
doaj +1 more source
Images, 2021 The author of the article, one of the acclaimed Polish cinematographers, describes his practical eforts involved in making two short documentary films on Holocaust directed by him.
Witold Stok
doaj +1 more source
Whisper networks in organizations: Sexual harassment protection through informal connections [PDF]
, 2022 This dissertation aimed to explore the communication networks women use to share information about sexual harassment and sexual harassers in their organizations. This study examined how women form and use whisper networks in their organizations.
King Johnson, Carrie Ann
core +1 more source