Can a Spanish spy speaking Hindi confuse an automatic speaker-recognition system? Which speaker characteristics are language dependent and which are language independent? A large part of the answer lies in the way these voice biometrics systems are created.
There’s a computer on every desktop and smartphone in every pocket. They have upgraded human capabilities, reach and connectivity. The world has become small. This is the future we dreamed of, this is the future that is already here. But what is going to happen next? Are we going to be dependent on AI? Have we become cyborgs?
Exclusively for Digital Forensics Magazine Phonexia’s CTO Petr Schwarz has written a comprehensive article about voice biometrics and its use in forensics. He discloses how the technology works and can be used in the daily routines of forensics experts as strong proof or evidence for presentation in a court of law.
The GDPR is a set of rules that regulates the processing of personal data related to individuals in the European Union. But how does the GDPR influence call centers, banks, insurance companies and other institutions that use voice biometrics?
Digital assistants are slowly integrating themselves into our homes, but they are far from being truly intelligent. Companies are considering using voicebots in their customer support but are afraid that voicebots are still a bit too clumsy to talk with customers. How far off is the future of smart and highly cooperative robots? And how is a voice-first approach going to change our lives?
Phonexia has just released the new version 3.12 of its Speech Engine which comes with an improved Denoiser technology, now accessible also via REST API.
The prestigious Journal of the Acoustical Society of America has just published a scientific article evaluating the performance of Phonexia speech technologies in the most difficult conditions. The evaluations were undertaken in extremely noisy environments where the speech itself was barely audible.
Phonexia has just launched Deep EmbeddingsTM – the latest generation of its voice biometrics engine for speaker identification and verification. The new technology exclusively uses deep neural networks (DNN) to map voices directly to their unique small and fixed length records called voice-prints.