You're seeing this page as if you were . The main menu is still yours, though. Exit from immersion
Malt Strategy
Nouveau rapport
Malt Tech Trends 2026
Malt Strategy
Nouveau rapport
Malt Tech Trends 2026
Peggy SyloppPS

Peggy Sylopp

AI Engineer & Consultant (Audio & Speech)

850 €/jour
Berlin, DE
8-15 ans
Python
Speech Processing
Data analysis
AI Prototyping
Audio Signal Processing

Délai de réponse moyen : 1h

À propos de Peggy

I build AI systems for audio and speech applications that work in real-world environments, from prototyping to deployment.

My work combines machine learning, real-time audio processing, and user-centered design to create practical, high-impact solutions. I have experience developing AI-based personalization systems, mobile audio applications, and real-time voice interfaces.

I support teams in translating complex ideas into working systems — from initial concept and prototyping to implementation and evaluation in real-world contexts.

My focus areas include:
• Audio & speech processing (STT, TTS, signal processing)
• Conversational AI and real-time systems
• Machine learning models based on real-world user data
• Prototyping and applied AI development

In addition to implementation, I bring experience in project leadership and interdisciplinary collaboration, working across engineering, research, and applied domains.

I am particularly interested in projects involving conversational AI, audio technologies, and applications in healthcare and assistive systems.
Édition de logiciels
Services numériques et IT
Santé et bien-être

  • Allemand

    Bilingue ou natif

  • Anglais

    Capacité professionnelle complète

  • Italien

    Notions

Accepte de travailler sur site
Berlin (jusqu’à 50 km), Hamburg (jusqu’à 50 km), Leipzig (jusqu’à 50 km)

Expériences

  • sinceare UG (Fraunhofer Spin-off)
    Founder & Technical Lead (AI & Audio Systems)
    HIGH TECH
    mai 2022 - Aujourd'hui (4 ans et 1 mois)
    Berlin, Germany
    Led the development of AI-based personalization systems for hearing applications, focusing on real-world performance and user-centered design.

    Developed a mobile audio application (iOS, JUCE/C++) enabling real-time audio processing and interactive control of sound parameters, with a focus on low-latency performance and usability.

    Built machine learning models to predict user-specific sound preferences based on real-world data and listening environments, supported by data pipelines and feature engineering for audio-based models.

    Designed and implemented real-time audio processing systems, integrating ML components into functional, low-latency prototypes.

    Designed and conducted user studies to evaluate system performance in realistic environments, including speech intelligibility, listening effort, and user preference.

    Managed projects end-to-end, from concept and funding to implementation and real-world evaluation.

    Coordinated interdisciplinary teams across engineering, research, and clinical domains.

    Translated a patented AI method for individualized sound personalization into an applied software system.
    Machine Learning Data analysis Feature Engineering Audio Signal Processing User Research
  • sinceare UG (Fraunhofer Spin-off)
    AI Engineer – Conversational AI Systems
    EDITION DE LOGICIELS
    novembre 2025 - novembre 2025
    Additionally, developed a real-time conversational AI system (Voice Bridge / Hörstimme), implementing a full-duplex STT–TTS audio streaming pipeline in the browser.

    Built a low-latency audio processing system using Web Audio API, including speech detection and adaptive chunking strategies.

    Developed multiple streaming modes (interval, silence-based, hybrid) to optimize latency and user experience.

    Integrated backend services (FastAPI + STT/TTS APIs) with real-time playback via MediaSource API.

    → Result: end-to-end conversational AI system bridging speech recognition, synthesis, and real-time interaction.
    Conversational AI Speech Processing Real-time Systems Python Text-to-Speech (TTS)
  • Fraunhofer IDMT
    Project Lead – AI & Hearing Research
    EDITION DE LOGICIELS
    novembre 2017 - février 2021 (3 ans et 3 mois)
    Berlin, Allemagne
    Led a research and development project on personalized hearing technologies, from initial concept to proof-of-concept system.

    Conceived and led the project “Hear How You Like to Hear”, focusing on AI-based sound personalization.

    Secured public funding and managed project execution, including planning, coordination, and delivery.

    Coordinated interdisciplinary teams across engineering, research, and user-focused domains.

    Developed proof-of-concept systems for machine learning-based sound personalization, grounded in real-world user needs.

    → Result: patented AI-based method for individualized sound personalization.
    Machine Learning Project Management User Research Research and Development (R&D) Data science

Recommandations

Soyez le premier à recommander Peggy

Contribuez à la réussite de ce freelance en partageant votre expérience de collaboration avec lui.

Ces profils de freelance correspondent également à vos critères

AgathaA

Agatha Frydrych

Backend Java Software Engineer

4.7

(3)

2

BaptisteB

Baptiste Duhen

Fullstack developer

4.6

(4)

5

AmedA

Amed Hamou

Senior Lead Developer

4

(2)

7

AudreyA

Audrey Champion

Web developer

4.3

(3)

4

S’inscrire pour les voir

Formations

  • M.A. Public
    HUMBOLDT-VIADRINA SCHOOL OF GOVERNANCE
    2011
    M.A. Public
  • Diploma in Computer Science
    TU BERLIN
    2009
    Diploma in Computer Science

Catégories