LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 3 of total 3

Search options

  1. Book ; Online: Towards Measuring and Scoring Speaker Diarization Fairness

    Tevissen, Yannis / Boudy, Jérôme / Chollet, Gérard / Petitpont, Frédéric

    2023  

    Abstract: Speaker diarization, or the task of finding "who spoke and when", is now used in almost every speech processing application. Nevertheless, its fairness has not yet been evaluated because there was no protocol to study its biases one by one. In this paper ...

    Abstract Speaker diarization, or the task of finding "who spoke and when", is now used in almost every speech processing application. Nevertheless, its fairness has not yet been evaluated because there was no protocol to study its biases one by one. In this paper we propose a protocol and a scoring method designed to evaluate speaker diarization fairness. This protocol is applied on a large dataset of spoken utterances and report the performances of speaker diarization depending on the gender, the age, the accent of the speaker and the length of the spoken sentence. Some biases induced by the gender, or the accent of the speaker were identified when we applied a state-of-the-art speaker diarization method.
    Keywords Computer Science - Sound ; Computer Science - Computation and Language ; Electrical Engineering and Systems Science - Audio and Speech Processing
    Publishing date 2023-02-20
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Book ; Online: The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description

    Tevissen, Yannis / Boudy, Jérôme / Petitpont, Frédéric

    2023  

    Abstract: We describe the system used by our team for the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC 2022) in the speaker diarization track. Our solution was designed around a new combination of voice activity detection algorithms that uses the strengths ... ...

    Abstract We describe the system used by our team for the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC 2022) in the speaker diarization track. Our solution was designed around a new combination of voice activity detection algorithms that uses the strengths of several systems. We introduce a novel multi stream approach with a decision protocol based on classifiers entropy. We called this method a multi-stream voice activity detection and used it with standard baseline diarization embeddings, clustering and resegmentation. With this work, we successfully demonstrated that using a strong baseline and working only on voice activity detection, one can achieved close to state-of-theart results.
    Keywords Computer Science - Sound ; Computer Science - Computation and Language ; Electrical Engineering and Systems Science - Audio and Speech Processing
    Publishing date 2023-01-17
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  3. Book ; Online: Privacy Preserving Personal Assistant with On-Device Diarization and Spoken Dialogue System for Home and Beyond

    Chollet, Gérard / Sansen, Hugues / Tevissen, Yannis / Boudy, Jérôme / Hariz, Mossaab / Lohr, Christophe / Yassa, Fathy

    2024  

    Abstract: In the age of personal voice assistants, the question of privacy arises. These digital companions often lack memory of past interactions, while relying heavily on the internet for speech processing, raising privacy concerns. Modern smartphones now enable ...

    Abstract In the age of personal voice assistants, the question of privacy arises. These digital companions often lack memory of past interactions, while relying heavily on the internet for speech processing, raising privacy concerns. Modern smartphones now enable on-device speech processing, making cloud-based solutions unnecessary. Personal assistants for the elderly should excel at memory recall, especially in medical examinations. The e-ViTA project developed a versatile conversational application with local processing and speaker recognition. This paper highlights the importance of speaker diarization enriched with sensor data fusion for contextualized conversation preservation. The use cases applied to the e-VITA project have shown that truly personalized dialogue is pivotal for individual voice assistants. Secure local processing and sensor data fusion ensure virtual companions meet individual user needs without compromising privacy or data security.

    Comment: 10 pages, 1 figure, to be presented at https://ihiet-ai.org/, Lausanne in April 2024
    Keywords Computer Science - Human-Computer Interaction
    Subject code 303
    Publishing date 2024-01-02
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top