The first speech recognition systems were focused on numbers, not words. Across the globe other nations developed hardware that could recognize sound and speech. Speech recognition made several meaningful advancements in this decade.
The Speech Understanding Research SUR program they ran was one of the largest of its kind in the history of speech recognition. Instead of just using words and looking for sound patterns, the HMM estimated the probability of the unknown sounds actually being words. Speech recognition was propelled forward in the 90s in large part because of the personal computer. Faster processors made it possible for software like Dragon Dictate to become more widely used.
BellSouth introduced the voice portal VAL which was a dial-in interactive voice recognition system. This system gave birth to the myriad of phone tree systems that are still in existence today. Because it was an app, this put speech recognition into the hands of millions of people.
It was also significant because the processing power could be offloaded to its data centers. Not only that, Google was collecting data from billions of searches which could help it predict what a person is actually saying. The early part of this decade saw an explosion of other voice recognition apps. Today, some of the largest tech companies are competing to herald the speech accuracy title.
In , IBM achieved a word error rate of 6. In Microsoft usurped IBM with a 5. Shortly after that IBM improved their rate to 5. However, it is Google that is claiming the lowest rate at 4. The technology to support voice applications is now both relatively inexpensive and powerful.
With the advancements in artificial intelligence and the increasing amounts of speech data that can be easily mined, it is very possible that voice becomes the next dominant interface. At Sonix , we can thank the many companies before us that have propelled speech recognition to where it is today. We automate transcription workflow and make it fast, easy, and affordable. Sonix automatically transcribes and translates your audio and video files in over 37 languages.
Easily search, edit, and share your media files. Sonix is the best automated transcription software in We are a digital agency committed to inspiring commercially-focused companies to evolve their digital experiences, and to achieve more from their marketing spend. By combining skills across design , development , digital marketing and analytics our team offers a proactive, progressive and unified approach to delivering effective digital solutions.
We like to share our wisdom by running events and regularly write blogs on digital marketing, user experience and web development. Get amazing new articles and event notifications delivered straight to your inbox. What are you waiting for? Open in Google Maps. Blog Origins of voice search and voice recognition Origins of voice search and voice recognition. Meet the author He knows how to make the most out of your website and get you set up for search engine Want more tips and insight like this delivered to your inbox?
Sign up to newsletter. A little about us Recent articles. See all our articles. But with the release of Google Voice Search App for the iPhone in , voice recognition technology began to once again make major strides. In many ways, smartphones proved to be the ideal proving grounds for the new wave of voice recognition technology. Voice was simply an easier and more efficient input method on devices with such small screens and keyboards, which incentivized the development of hands-free technology.
In many ways, Siri is a prime example of Apple doing what it does best: Taking existing technology and applying a mirror-sheen of polish to it. As more and more users opt for mobile devices instead of desktop computers, voice recognition is becoming increasingly central to our day-to-day lives.
And beyond entertainment or personal use, there have also been many exciting developments around how voice recognition is used in business and commerce. Voice recognition technology powered by AI can now be used to transcribe phone calls, and even predict the outcome of a conversation based on its tone and the words used.
0コメント