Speech Technologies

ANKA Advanced Technologies INC. > Speech Technologies

AI-Driven Speech Technologies


Our Speech Analytics unique combination of AI and Speech Technologies.

Unique Features

  • Zero 3rd party license cost (Can work on all  Linux operating systems, only open source libraries are used)
  • We consume less system resources.
  • We perform text and content analyzes over NoSQL systems. We make these analyzes faster than global companies with similar capabilities.
  • All parts of our system are open to integrating with 3rd party software as API.
  • Price / Performance Leader

ANKA FISA – Forensic & Intelligence Speech Analysis

The ANKA-FISA offers all analyses tools under one roof to analyze and examine all kinds of audio acquired through transfer from any environmental bug, an interception from a phone or radio or through any other method in order to combat terrorism and organized crimes.

Unique Features

The FISA’s Modules are designed with field experts from intelligence and forensics. At the same time, its capabilities are perfectly enough for all speech and audio professionals and practitioners

  • It can find the target speaker among thousands of unlabeled records (Speaker Identification)
  • Clarify the speech from all noises and non-speech sounds (Audio Enhancement)
  • Searching for mounting marks at suspected points (Analysis)
  • Segment all speakers in a record and group all utterances individually (Speaker Diarization)
  • Verify an unknown speaker by comparing with possible known suspected records (Speaker Verification)
  • Convert all utterances into text (Automatic Speech Recognition, STT)


Medical Dictation and Transcription Software for Healthcare Professionals

Unique Features

ANKAMED-SR Automatic Speech Recognition System (ASR) is the conversion of sound to text. Speech Recognition Systems are developed using Artificial Intelligence Technologies.

  • ANKAMED-SR is a high-performance Medical Turkish Speech Recognition technology specific to the Doctors and other hospital staffs.
  • It allows any medical report that becomes a major workload in the hospital to be created by speaking in a few minutes.
  • At the same time, reports in audio recording are transcribed in a short time. Considering that 1-hour audio recording is transcribed in 8 hours, it gives hospital staff high production efficiency.
  • Patient satisfaction is achieved by rapid report production
  • Prevents loss of revenue caused by late production of reports