Voice recognition

From iDigBio
Jump to: navigation, search

Voice recognition software allows for hands-free control of software and textual data entry. This capability has potential for integration into digital workflows for control of workflow components (cameras, software) and for data entry (dictation, metadata).

Voice Recognition Software

Nuance Dragon Naturally Speaking - Windows

Nuance Dragon Dictate - Mac

Microsoft Windows Speech Recognition - Windows 7 and Vista

CMU Sphinx open source toolkit for speech recognition - Linux

See also:

Tools for integrating voice recognition software

PySpeech - Python module for accessing basic functions of Windows Speech Recognition.

NatLink - Python module for integrating with Dragon Naturally Speaking. Requires NatLink and Unimacro.

Projects using voice recognition

Project: Rapid inventory (prototype)

Contact: Jason Best - jbest(at)brit.org

Description: This project is exploring how voice recognition might be used to perform a rapid inventory of an herbarium collection. The data captured is limited to a count of specimens representing each species in a geographic location.

If you are using or exploring voice recognition in a project, please add it here or contact Jason Best if you don't have an iDigBio account for editing this wiki.