Voice Technology

Voice Technology has a rich history of development that has led it to what it is today. For the past 70 years, mankind has been engaged in the study, development and implementation of Voice Technology. It is now at the heart of modern life, giving us the ability to perform tasks just by talking to a device.

Evolution of Voice Technology over the years:

In 1952, the first speech recognition system designed by Bell Laboratories was known as the "Audrey" system and could only recognize a single voice digit spoken aloud. It was thought that Audrey could be used for hands-free telephone calling. But Audrey was not the expected success among users due to its large size, increased power requirements, and high production and maintenance costs.

Ten years later, IBM introduced the Shoebox, which was able to understand and respond to 16 spoken English words, as well as the numbers 0-9. "Like Audrey, the device attempted to recognize and act on the specific vowel frequency in each spoken digit"

In the 1970s, the Advanced Research Projects Agency of the US Department of Defense began the Speech Understand (SUR) research program, which focused on the development and research of speech recognition technology at Carnegie Mellon University. DARPA's goal was to develop speech recognition technology that could understand up to 1,000 words. As a result of research and work done by SUR in the 1970s, Carnegie Mellon was able to develop the "Harpy" speech system in 1976, which understood more than 1,000 spoken words in English. Harpy processed speech that followed vocabulary, pronunciation and pre programmed grammatical structures. Like the voice assistants available now, Harpy returned an "I don't know what you said, please repeat" message when it couldn't understand the speaker. But unfortunately, like previous systems, Harpy was still limited in its ability to understand natural language.

In the late 1970s, the first commercial IVR (interactive voice response) application was released, designed and developed by Steven Schmidt. IVR systems are automated computer telephone systems that use specialized telephone hardware and the manipulation of a digitized voice.

In the 1980s, the development of the Markov model helped further the research and development of speech technology by using statistics to "determine the probability that a word originates from an unknown sound". This statistical method was revolutionary because "instead of using only words and looking for sound patterns, HHM estimated the probability that unknown sounds were words."

The 1990s brought huge technological advances, including the masses having greater access to both personal computers and speech recognition technologies. DragonDictate, developed by Dr. James Baker, is the first consumer speech recognition product to use discrete dictation methods that required the user to pause between each spoken word. Later in 1997, Dragon NaturallySpeaking, the first continuous speech recognition product available to consumers, entered the market. Dragon NaturallySpeaking was able to recognize and transcribe natural human speech at a rate of about 100 words per minute. Dragon NaturallySpeaking did not require users to pause between each word, as Dragon Dictate required. "By pioneering continuous speech recognition, Dragon has virtually pioneered the use of speech recognition for document creation." Dragon NaturallySpeaking is still available for download and is used by people such as medical professionals. Additionally, in the 1990s, call centers began investing in computerized telephony integration (CTI) with IVR systems, which led to the birth of the automated telephone call.

The first built-in voice recognition software and voice-activated control software for Apple computers were introduced as part of Mac computers. In the early 2000s, Microsoft released a similar feature on its computers.

Recent Evolution of Voice Technology:

From 2010 to present, the growth of research, development and implementation of Voice Technology has skyrocketed. The decade began with IBM's Watson, a computer response system capable of understanding natural language. Later that year, Apple introduced Siri to all of its mobile devices. Once Siri was launched, the implementation of natural language speech recognition technology took off, and in 2013, Microsoft introduced Cortana, a Siri-like virtual assistant that was to be implemented on all Windows devices.

Shortly after, Amazon introduced the Alexa device for Prime members only. In 2015, Amazon launched in the United States, with Google Home launching the following year. Now, we're seeing virtual assistants promulgated as commonplace in both our homes and cars.

What is Voice Technology?

Voice recognition technology is a software program or hardware device that has the ability to decode the human voice. Sometimes called voice-activated or speech recognition software, this technology has become increasingly popular in recent years. These devices are built in where they are needed, to make commands, find information or make records easier. In fact, the size of the voice commerce market is expected to grow significantly in the coming years.

As voice-activated technology becomes more widespread and accessible, we think it's important for you to understand more about it. After all, this technology is changing the way people live, work and interact. It will most likely become an integrated part of our everyday life.

How does Voice Technology work?

Although using Voice recognition Technology seems as simple as saying a few words, the way it works is actually quite complex. First, voice recognition software filters through the sounds you speak and translates them into a format it can "read." It then analyzes that "translation" for meaning and uses that information — along with the algorithm and previous inputs — to guess what you said.

If there is only one person using a voice-activated technology, its ability to understand and understand the meaning will improve over time, becoming more and more accurate. Things get much more complex when we consider other users, different languages and dialects, and other factors that can affect human speech. Even common changes, such as background noise or vocal inflections, can affect how voice-activated technology understands a speaker.

Many types of voice-activated technology "learn" language in the same way that children do. The Linguistic Society of America claims that “children acquire language quickly, easily, and without effort or formal teaching. It happens automatically, and children who are never spoken to will never acquire language.” In other words, children learn based on how other people use language with them and around them. Similarly, voice recognition systems must receive language input and interact with it to learn how to recognize patterns and make connections in human language. Without this introduction and training, many voice recognition systems probably could not work as well or as accurately as they do today.

Despite these difficulties, various voice recognition systems continue to constantly improve and advance in their ability to understand human voice. For example, at the end of 2016, Microsoft's voice recognition technology reached a level of understanding similar to that of humans themselves, and Google's own voice recognition software reached a recognition accuracy level of 95% not much time after. As researchers continue to study, train and develop voice recognition technology, it could become even more accurate in the future.

Types of Voice Technologies - there are a variety of different types of systems that fall under the larger umbrella of voice-activated technology:

Speaker-dependent systems: require preparation before use and therefore depend on the operation of a speaker. Users may need to read a series of words, phrases, and sentences to help train the system.
Speaker independent systems: requires no training before use and is already able to understand the voices of most users. Many popular voice assistants use speaker-independent systems.
Discrete voice recognition: Asks users to say words one at a time or with pauses between each word, as the system can only understand words and their meanings individually.
Continuous Speech Recognition: Allows users to speak at a normal pace when interacting with the system.
Natural language: Can understand a user's words and their meaning and can also respond to them, provide answers to questions, complete commands or provide requested information.

Where and how Voice Technology can be used:

Although only recently in widespread use, voice activation and recognition technology already has a multitude of applications in various aspects of our lives. In fact, it's become so popular in such a short time that you've probably already used or interacted with voice-activated technology. The most popular applications for voice technology include:

Cars: Many cars now have voice-activated technology built right into the vehicle. These include devices such as smart car speakers and connected car hotspots to enable easier and safer hands-free driving.
Home Appliances: Many appliances, devices and systems are now connected to the internet and to each other, making it easier than ever for people to control, protect and enjoy their homes. Many of these smart home devices, such as thermostats and security systems, also use voice activation for the same purpose.
Laptops and tablets: It is now common for laptops and tablets to have voice recognition built into the device so you can embrace a hands-free experience when you need or want it.
Personal digital assistants: They are among the most popular uses of voice-activated technology. Many—like Google's Hey Google and Apple's Siri—are built right into popular smartphones, so you can use them no matter where you are or what you're doing.
Wearable technology: Similarly, wearable technology such as fitness trackers and smartwatches also allows you to use voice recognition whenever you have your device with you. This can make these devices easier to use, as they tend to have small screens and buttons.

Today Total Technologies provides Voice Technology for your business. Contact us today, call +40 372 317 714 to find out how Voice Technology can become your competitive advantage.

Did you know?

Voice Technology

See news