Adding intelligence to Speech Recognition
Our NLI technology offers so much more than simple “voice recognition” or “automatic speech recognition” tools, though we provide that too if you want. We like to say NLI adds true intelligence to voice commands.
- Automatic Speech Recognition (ASR) – also known as computer speech recognition or speech to text – converts spoken words to text.
- Text to Speech (TTS) – converts text to spoken words.
ASR vs. NLI
Whilst ASR converts spoken words to text and is often used in applications such as voice dialing and dictation tools, it doesn’t have human-like intelligence. It can’t qualify a question by asking for more information. It can’t remember. It can’t search other information sources for information. In summary, it’s not able to deliver intelligent solutions.
However, with NLI technology such as Teneo, we are able to make a machine understand questions no matter how they are phrased. It also has the capability of remembering information and keeping it for later in a conversation. So you can ask complex questions in free-format, natural language and Teneo will learn, reason, understand, and then apply this knowledge to act on what has been said.
For example, with ASR your Xbox game will understand “stop game”, but only that one command spoken in one specific way. With NLI implemented you could say “I want to stop” / “please, let’s quit” / “I don’t want to play anymore” / “this is boring, let’s do something else” and more, and the program would understand all these inputs as meaning the same thing, asking further qualifying questions if necessary. NLI has added the intelligence which makes it possible for you to speak to your game console in exactly the same way you would talk to a person.
How ASR, NLI and TTS work together
The Teneo platform supports spoken dialog with the use of ASR to handle speech as an input channel; and TTS to produce spoken output. The Teneo Interaction Engine handles the Natural Language Understanding (NLU) and Dialog Management in order to make the NLI solution understand, reason and react (as opposed to simply performing a voice search).
Artificial Solutions specializes in the complex field of artificial intelligence and natural language interaction and has chosen to partner with a range of providers that deliver speech technology. The Teneo Interaction Engine uses an API that links to ASR vendors to capture voice on the device and send it to the ASR engine to get a written output/suggestion back of what was most likely said. The ASR vendor can provide this service in the cloud or the ASR engine and the TTS engine can be hosted by Artificial Solutions.
The Teneo platform’s robustness in NLU and Dialog Management precisely fill the gaps left by ASR systems to create a truly natural experience, using a number of proven ASR-handling strategies to increase the quality and the end-user experience. Combining the capabilities of the Teneo Natural Language Interaction platform with the capabilities of ASR systems leads to a superior user experience; a truly natural speech-based interaction between a human and a device.