Overview

The KeenASR Software Development Kit provides on-device automatic speech recognition functionality for mobile devices running iOS or Android operating system.

Speech recognition is performed locally on the device; no internet connectivity or cloud support is required. The SDK is based on a state-of-the-art Deep Neural Network decoder and includes acoustic models.

The SDK provides Deep Neural Network (DNN) decoders and a variety of DNN acoustic models. In addition, it includes an API for creating language models on the device for small to medium-size recognition tasks (up to several thousand words). For large vocabulary dictation-type tasks, language models and decoding graphs can be created ahead of time and used by the SDK. For domain specific large vocabulary use cases, large amounts of domain specific text data might be required to build appropriate language models.

The SDK also supports trigger phrase functionality, which is viable for sessions up to two hours. The trigger phrase implementation does not currently support always-on (24x7) listening use cases, especially on battery-powered devices.

Platforms and Development Tools Support

In addition to the Objective C iOS framework and the Android Java AAR SDK, we also provide instructions on how to use the Objective C framework in Swift and a Unity plugin, which provides a C# interface to both the iOS and the Android versions of the SDK.

The iOS and Android SDKs are on separate release paths. The Unity plugin is typically updated when there is a new release of either iOS or Android SDK.

Keen Research customers can also leverage Dashboard, a cloud-based tool for on-device ASR development support. KeenASR, in conjunction with Dashboard, provides seamless synchronization of on-device data, and cloud-based access to audio recordings and speech recognition metadata for further analysis and debugging, ability to transcribe and score responses, etc..

Trial Version of the SDK

Keen Research provides trial version of the SDK for both iOS and Android, as well as ASR Bundles (acoustic models) that can be used with the trial SDKs.

Language Support

Currently, the SDK supports English and Spanish out of the box. Additional ASR Bundles for most major spoken languages can be provided upon request within 6-8 weeks.

Keen Research can also provide customized ASR Bundles that work better in specific acoustic environments, with specific population, or have a smaller memory footprint and CPU utilization.

To get started, we suggest you review the Getting Started and Glossary pages, and then move on to the documentation for your platform of interest.