Language Sample Collection in AAC

Language Sample Collection

The collection of language samples is a foundational element of AAC evidence-based practice. Language activity monitoring (LAM) makes this a feasible task. Click AAC clinician perspective on the value of language sample collection to learn more.

(As with all language sample collection for clinical practice or research, informed consent must be obtained.)

Read more about Rights and Privacy here:

Language Activity Monitoring (LAM)

Language activity monitoring (LAM) is the automatic recording of the content and time of language events generated using AAC systems. Language samples can then be analyzed for the support of AAC evidence-based practice. The primary LAM implementations are 1) as a built-in feature in modern AAC systems and 2) as software to allow a PC to act as a LAM (U-LAM).

LAM data consists of two required fields and one optional field. For each language event, a time stamp and the content are available. Analysis of a language sample containing this information yields much information of clinical significance. The optional field is a three letter mnemonic indicating how the language event was generated in the AAC system. It has been found that the method used to generate language can have a dramatic impact on communication performance. This optional field provides information that addresses this issue.

The LAM file can start with a header. The header may include components such as the name and version of the AAC system and a privacy notice. An example is presented here:

### CAUTION ###
The following data represents personal communication.
Please respect privacy accordingly.

Language Activity Monitor “device name”
Version 2.00 07/26/01
ACME AAC Company

09:27:17 OWS “I “
09:27:19 OWS “am “
09:27:22 SMP “hungry “
09:27:24 OWS “and “
09:27:26 OWS “I “
09:27:29 SMP “want “
09:27:34 SPE “s”
09:27:36 SPE “o”
09:27:38 SPE “m”
09:27:43 WPR “some “
09:27:49 DWP “something “
09:27:51 OWS “to “
09:27:58 PAG “eat “

Data Logging

Data logging is a term applied to the automatic recording of data that can be analyzed to produce a time-stamped transcript of what has been generated using an AAC system.

Note: The counting of key activations is not considered to be data logging since no time information is available and a transcript cannot be generated using that information.

Data logging generally has at least two components. The first is a time stamp that indicates the time of an action. The time can be absolute real time in a 12- or 24-hour format. If the AAC system does not have an internal real time clock, a clock that starts to run when the AAC device is turned on can suffice. A resolution of at least one second is needed for most clinical needs. However, some applications, such as research, may benefit from higher resolution time stamps.

The second component of a data logging record is the activity that occurred at the indicated time. Many clinical summary measures of communication performance can be calculated using only the content of what is generated. However, some research may benefit from the recording of other activity and information.

Two data logging standards are in use in AAC. Language Activity Monitoring (LAM) is a method that records the time and content of communication. An optional field indicates the language representation method employed for each output. More information on LAM, including an AAC clinician perspective, is available at:

Another data logging standard was developed in the Rehabilitation Engineering Research Center on AAC (AAC-RERC). The AAC-RERC standard provides for the recording of many different activities and, while significantly more complex, may be more useful for some research.

For Developers

Welcome to the AAC Data Logging Consortium!

We want to thank you for joining us in our efforts to share best standards, practices and open-source software related to log file management for AAC systems. This consortium has been organized as an open collaboration by Eric Nyberg, Carnegie Mellon University School of Computer Science, and Katya Hill, University of Pittsburgh and AAC Institute.

This welcome message is being sent to the following manufacturers and/or app developers listed alphabetical order who have accepted our invitation to participate in this consortium:

• AACorn
• AssistiveWare
• Cough Drop
• LC Technologies
• Lingraphics
• Prentke Romich Company
• ProxTalker
• Saltillo
• Speak For Yourself
• Therapy Box

Those of you currently representing your company should consider adding to the group any person(s) who will be designing and/or programming the data logging feature(s) and any monitoring options on your applications or systems. Please, send the new names and contact information to us if you can think of anyone else who can take advantage of this opportunity. To represent academic and clinical perspectives, we plan to invite several individuals who are part of our original linguistics and language technology research group, who we hope will also be joining us.

Consortium information, standards, specifications, codes, and open source software will be shared with member organizations and developers via a Github repository hosted by the Open Advancement for Question Answering: