The Verbyx Blog

Automatic Speech Recognition

You never change things by fighting the existing reality. To change something, build a new model that makes the existing model obsolete.

Buckminster Fuller
Pilot Headset

What is an Acoustic Model and Why You Should Care?

An acoustic model is used in automatic speech recognition to represent the relationship between an audio signal and the phonemes or other linguistic units that make up speech. A well trained acoustic model (often called a voice model) is critical in the performance of an

Read More »

Dealing with Out-of-Grammar Inputs

Introduction The previous post introduced the topic of unsupported phrases also called out-of-grammar (OOG).  The Impact of Unsupported Phrases.  The post explained that OOG is not specifically a speech recognition problem. However, serious thought and consideration of dealing with out-of-grammar inputs are vital. The consideration

Read More »

The Impacts of Unsupported Speech Phrases

In earlier posts, we discussed how we might specify and measure speech recognition accuracy when using a constrained grammar model. The definition of the required phrases was also explored. If we could trust the users of our system only to use the supported phrases, we

Read More »

ASR Accuracy – Specification and Definitions

ASR Accuracy and Usability In an earlier post A Word About Accuracy, we discussed various ASR accuracy methods used in requirements specifications and testing. Why word accuracy is a poor choice in simulation and command & control applications, was explained in the post “Word Error

Read More »
F35 Cockpit

Supported Phrases in an ASR System

Supported Phrases – An Introduction to Requirements Requirements documents for simulators often contain very loose definitions for supported phrases. For example, the system shall support all appropriate phrases defined in document XXX and locally supported terminology. Command & Control applications do not typically have the

Read More »

Word Error Rates are Misleading

Word Error Rates are Misleading The system must have a Word Error Rate (WER) of 2% or less. This appears to be a reasonable requirement. With such a small error rate, surely, I can be confident that my speech recognition implementation will be a success?

Read More »

Contact

Occasional Newsletter

Scroll to Top
Scroll to Top