Summary
- Profile Type
- Technology offer
- POD Reference
- TOES20250219030
- Term of Validity
- 19 February 2025 - 19 February 2026
- Company's Country
- Spain
- Type of partnership
- Research and development cooperation agreement
- Commercial agreement with technical assistance
- Targeted Countries
- All countries
Contact the EEN partner nearest to you for more information.
Find my local partner
General information
- Short Summary
-
Spanish SME offers an AI-powered solution for real-time detection of artificially generated voices and AI deepfake voice cloning.
This technology effectively identifies sophisticated voice impersonation attacks, protecting against fraud in various sectors.
The solution is available as a Software Development Kit (SDK) for easy integration. - Full Description
-
A Spanish SME has developed an innovative AI-powered solution to address the growing threat of fraud and misinformation caused by sophisticated AI deepfake voice cloning technology. This technology is designed for real-time detection of artificially generated voices used in cybercrime, phishing attacks, and fake news campaigns.
The solution tackles the problem of modern machine learning making artificial voices virtually indistinguishable from real human voices. It analyzes both Text-To-Speech (TTS) and Voice Modulation (voice changer) attacks, detecting subtle audio signal features present in real human voices but absent in synthetic voices, and vice versa.
Key features include:
• Effectiveness against both TTS and advanced vocoders
• Language independence
• State-of-the-art AI recognition engine
• Advanced audio feature extraction
• Easy-to-integrate API for on-premise solutions
The solution finds application in:
• Detecting fake news in social media, radio, and TV
• Preventing bank heists and phishing attacks
• Verifying the authenticity of speakers in remote communications
The SME seeks partners for technology integration, licensing agreements, or joint development projects to expand application areas and enhance the technology further. - Advantages and Innovations
-
This solution offers several advantages over existing methods for detecting AI-generated voices:
• Real-time detection: Enables immediate identification of synthetic voices, preventing fraud and misinformation in real-time.
• Effectiveness against both TTS and vocoders: Provides comprehensive protection against various types of voice cloning attacks.
• Language independence: Detects voice impersonation attacks regardless of the language used.
• Advanced AI recognition engine: Leverages state-of-the-art machine learning algorithms for high accuracy and reliability.
• Easy integration: Distributed as an SDK with a highly efficient C++ API for seamless integration into diverse applications. - Stage of Development
- Already on the market
- Sustainable Development Goals
- Goal 16: Peace and Justice Strong Institutions
- Goal 9: Industry, Innovation and Infrastructure
- Goal 8: Decent Work and Economic Growth
- Goal 17: Partnerships to achieve the Goal
- Goal 3: Good Health and Well-being
- IPR status
- Secret know-how
Partner Sought
- Expected Role of a Partner
-
Integration of the mentioned technology into existing security solutions, development of new applications, licensing and distribution.
Ideal partners may be security solution providers, companies in the fintech, media, telecommunications, or cybersecurity sectors interested in enhancing their products with AI-powered voice cloning detection. - Type and Size of Partner
- SME 11-49
- R&D Institution
- Big company
- SME 50 - 249
- Type of partnership
- Research and development cooperation agreement
- Commercial agreement with technical assistance
Dissemination
- Technology keywords
- 01003006 - Computer Software
- 01003017 - Speech Processing/Technology
- 01003003 - Artificial Intelligence (AI)
- 01003009 - Data Protection, Storage, Cryptography, Security
- Market keywords
- 02007021 - Other Artificial intelligence related
- 02007016 - Artificial intelligence related software
- 02008001 - Voice synthesis
- 02008002 - Voice recognition
- Targeted countries
- All countries