• Jacek Jarmulak

Competitive Advantage of Custom Acoustic Models

Updated: Jul 1, 2020

There is no doubt that there is value in the data, in particular in data that can be used to train AI models. That is one of the reasons why Google offers their Speech-to-Text service at two price points, one with data logging and and one without, see table below.

Voicegain speech-to-text platform does not capture or use any customer data (while still being able to offer low ASR pricing). Moreover, Voicegain platform enables our customers to use their data to train custom Acoustic Models. As result, our customers benefit in two ways:

  • They are able to use ASR with their own custom Acoustic Model(s) with speech-to-text accuracy higher by several % compared to our Base Models.

  • Because, neither their data not custom Models are shared with anyone (neither Voicegain, nor any other Voicegain customers), the higher accuracy translates directly into competitive advantage.

Basically, by retaining ownership of the data and the custom Acoustic Models, our customers benefit from higher ASR accuracy in general, and higher accuracy than their potential competitors in particular.

This is different compared to using Goggle speech-to-text with data logging enabled. First of all, there is no guarantee that specific speech data logged by Google will actually be used to improve the model. And if it is used, then it will be benefiting everyone, thus also potentially the competition.

123 views0 comments