Voice and sound set of data it’s our labeling goal.

• Sound analysis

  Information from sound signals is analyzed, classified, compared and stored.

• Voice analysis

  In this case, we analyze speech sounds. It is used, among others, to identify or recognize speech. Artificial neural networks are usually used for recognizing speech. It is widely used in medical analysis and interlocutor’s verification.

• Transcription

  It is about converting human speech to text. It became available thanks to speech recognition.

• Corrective transcription

  Process of the conversion of human speech into text using correction. Every word is checked and possibly corrected.

• Translation and location

  In translation, we translate the words of the source language into text and then translate the text into another target language. Localization, on the other hand, adjusts the translated words to a specific region, adapting its meaning to its cultural specificity. This makes the translated words more understandable and easily absorbed by the recipient, for example, British English and US English have different translations for similar sentences.