Summary Comparison of LENA Parent, Pro and Research Versions
Additional Features for Researchers!
The LENA Research version provides the ability to:
- Export all audio files to
Transcriber.
LENA Software automatically categorizes speakers and non-speech sounds – so you don’t have to! Reduces transcription time significantly!
- In-Depth Analysis: For every audio recording, the LENA software produces a detailed data file in XML format, which gives users segmented information on speaker identification and much more.
- In addition to the standard reports, LENA Research shows ‘behind-the-scenes’ information on each file, such as: time,
date, segmentation categories, and demographical information.
Advanced Data Extractor (ADEX)
The Advanced Data Extractor (ADEX) tool allows already exported data to be further analyzed in Excel. This allows
colleagues or assistants to easily sort, view and analyze data.
Export your data into:
- Excel
- .TRS and .CHA: Audio files can be put into Transcriber or CLAN freeware/software, listened to and transcribed.
- ITS (Infoture Time Segmented file)*
*The ITS file automatically separates the audio into speech/noise blocks so you can easily identify:
- Key child (wearing the DLP)
- Other child(ren)
- Male adult
- Female adult
- Noise & TV
- Silence
Download ADEX
| Features/Reports |
LENA Parent |
LENA Pro |
LENA Research
|
|
Adult Words
|
X
|
X
|
X
|
|
Conversational Turns
|
X
|
X
|
X
|
|
Developmental Snapshot
|
X
|
X
|
X
|
|
Automatic Vocalization Assessment (AVA)
|
X
|
X
|
X
|
|
Child Vocalizations
|
|
X
|
X
|
|
Audio Environment
|
|
X
|
X
|
|
Composite Report
|
|
X
|
X
|
|
Five-minute sequence view
|
|
X
|
X
|
|
Audio listen and view
|
|
X
|
X
|
|
Re-assignment of DLP
|
|
X
|
X
|
|
Client/Subject Management
|
|
X
|
X
|
|
Export Report Elements
|
|
X
|
X
|
|
A D E X
|
|
|
X
|
|
View and Export ITS File
|
|
|
X
|
|
Export .trs file for use
with Transcriber and
export .cha file for
use with CLAN*
|
|
|
X
|
The Infoture Time Segmented (ITS) File
The Infoture Time Segmented (ITS) File is available with the LENA Research version. An ITS file is a text file
in XML format that contains the information generated by the audio-processing. It’s created as a final output from the LENA
algorithm software after analyzing a given audio file. The LENA Application software then picks up this file for creating graphs
and charts in a user-friendly manner for viewers. Hence, this file acts as a liaison between the algorithms and the application software.
Each ITS file provides the following:
-
Segmentation information of the audio file:
- Identification of speakers and characteristics in audio segments –
adult male, adult female, key child, other children, electronic sounds,
overlapping sounds, distant sounds, noise, and silence.
- Analysis of audio segments to determine Adult Word Counts and Key
Child Vocalizations for corresponding segments.
- Identification of conversations: beginnings and endings of conversations, intermediate pauses that occur in between
conversations, speakers involved in conversations – the initiators, responders, and floor holders.
- Identification of conversational turns – back and forth between the adults and the key child
- Analysis of background sounds which include noise, silence, TV, radio, any electronic and
recorded sounds, distant speech and overlapping sounds.
- Description header of the audio file includes audio characteristics, and the beginning, end, and paused segments
that occur in the time span of an audio file.
- Summary and description of the key child, ex. child’s gender and age.
-
Time summaries
- LENA Research Reports provide hourly and five-minute summaries. However, for a more in-depth analysis one can
detail down to the vocalization level using the segmentation information of the ITS file.
Export .trs file for use with Transcriber software or .cha files for CLAN software
View, edit, and save audio files (Up to 16-hour audio files).
-
Audio files include segmentation identification, including:
- Environment sounds: silence, noise, overlapping speech, TV, other electronic and background sounds
- Voice recognition and identification (adult male/female, key child and other child)
- Adult word counts for all adult male and female segments
- Key child sounds with special designation for:
- Cry
- Vegetative and fixed signals
- Meaningful vocalizations together with their durations and counts.
-
TRS and CHA file will have four tiers:
- Recording level: Indicates when the DLP has been started, stopped and restarted
- Conversation and Pause level: Indicates filler regions, also known as Pause regions, as well as Conversation regions
- Segmentation ID level: Indicates each individual speaker or segmentation id, ex. MAN, FAN, TVN, etc.
- Context transcription level: Initially empty, allows user the opportunity to transcribe the context if they desire
-
Viewing audio requires:
- A .trs file ( an XML text file) or .cha file (a CHAT transcription formatted text file from The CHILDES Project*)
- A .wav or .raw audio file
- Transcriber Software, version 1.5.1 or higher or CLAN software
To download a free copy of Transcriber software, go to: http://sourceforge.net/
To download a free copy of CLAN software, go to: http://childes.psy.cmu.edu/clan/
(Whether you are a Transcriber user or CLAN user, either software allows you to transcribe the context speech, if desired.)
Next 