The speech-to-speech (STS) technology enables substituting a speaker’s voice with another one while preserving the original speaking style, intonations, pauses, prosody, and other conversational characteristics. Its main distinctive feature from similar technologies lies in the fact that it does not use TTS (text-to-speech) synthesis for generating a new speech but applies changes to the speaker voice’s vocal characteristic in the original record. This way, STS eliminates typical TTS-generating problems like pronouncing unknown words, lack of inflections, and robotic voice sounding.
STS technology applications are rather versatile. Among the most common ones are international professional presentations (where it is used to improve the quality, clarity, and impact of the speaker’s voice) and the entertainment sphere (where it helps to generate characters’ voices and voice-overs in films, games, and animations). Also, this technology can influence victim assistance and witness protection, altering the speaker’s voice so that it becomes unrecognizable while retaining the original speech’s meaning and nested emotions. In addition, STS is utilized to facilitate communication for patients who have undergone throat surgery, making their electronic “voice box” implants sound more natural, articulated, and intelligible.
Obviously, these examples of STS employment are just a glimpse of the vast opportunities available in this rapidly growing field, which encompasses a wide range of industries and specializations.
