This paper presents a sequence-to-sequence voice conversion (S2S-VC) algorithm which
allows to preserve some aspects of the source speaker during conversion, typically its …

Emerging smart devices, such as smart home and augmented/virtual reality systems, are
reforming our living experience by automating our daily routines and interacting with us …

In today's telecommunication world sharing the data becomes very easy. It is a bit-
complicated in converting the text documents to voice assistance even proposed a lot of …

En este artículo se muestra el comportamiento de varios asistentes personales (Smart
Personal Assistants, SPAs) en diversos aspectos relativos a la seguridad ya la privacidad …

For machine learning (ML) to work well, there is a need for large amounts of good quality
training data. Obtaining such data is often the key bottleneck for the entire ML development …

Text-to-speech synthesis (TTS) is a task to transform texts into speech. End-to-end TTS is
one of the TTS frameworks, and its unique approach is characterized by using only a single …

Computer-generated synthetic voices are increasingly growing indistinguishable from
human voices. While these high-quality synthetic voices open new horizons for the …

Fortschritte im Bereich der künstlichen Intelligenz und neuronalen Netzwerken haben zur
Generierung von realistischen gefälschten Inhalten geführt. Diese neue Technologie mit …

With the prosperity of artificial intelligence, research on machine learning becomes a hot
issue globally. Generative Adversarial Networks expose the huge security risks of machine …

A method is provided for identifying synthetic “deep-fake” audio samples versus organic
audio samples. Methods may include: generating a model of a vocal tract using one or more …