A Brief Introduction to Speech Technology

A Brief Introduction to Speech Technology

By Mortaza Doulaty

Speech technology has been a hot research topic for more than five decades; it tries to duplicate and respond to a human’s voice. It is a valuable tool for both human-to-human and human-to-machine communication. Speech technology is becoming more popular lately, and almost everyone benefits from the advances in this technology. In this series of articles, various aspects of the technology – its past, current state and future – will be discussed.

Speech technology can be divided into these categories:

• Speech synthesis which is the artificial production of human speech

• Speech recognition which converts the spoken words into text

• Speaker recognition, as the name suggests, is for recognizing the speaker

• Speaker verification is for verifying the identity of the speaker

• Multimodal interaction which offers alternative ways of interfacing with devices

In digital assistant systems like Apple Siri, Google Now, Microsoft Cortana and Amazon Echo a combination of all of the above technologies are involved and used. Before 2010, this technology was not very popular and was not known to many people. It was quite limited and was mostly used for voice dictation software such as Nuance’s Dragon NaturallySpeaking. Apple Siri was a game changer in 2011 and re-introduced the world to the high potentials of speech technology. Since then, other tech giants like Google, Microsoft and Amazon have introduced their speech tech-based products. Some of these products are no longer just an app on your cell phone (like Apple Siri and Google Now). Microsoft has announced that Cortana (which was originally developed as an app for Windows Phone) will be a part of Windows 10. Also, Amazon introduced Amazon Echo, which is a voice command hardware device. Other interesting uses of speech technology can be seen in Microsoft Skype’s translation system, which is a voice-to-voice real-time translation system.

Speech technology is not just limited to voice dictation software or personal digital assistant applications. In fact, it has many other potential uses such as in the health sector. In upcoming articles, other applications of this technology will be revealed.



Never miss an insight

Get insights delivered right to your inbox

More of Our Insights & Work

Never miss an insight

Get insights delivered right to your inbox

You have successfully subscribed to our newsletter.

Too many subscribe attempts for this email address.