Content

User Guide

Latest Update

 

Modules

BASIC module

OPENSET module

PHONE module

SRT module

MCI module

TEST module

 

 

 

 

Sound Express™: Openset Module

 

This is one of the advanced module developed for Sound Express Auditory Training Software. This module provides several advanced taining protocols targeted at different listening situations. Different from closed-set phoneme recognition, there is no explicit choice for each trial. The chance level is close to zero. There are six training groups in this module, which target at different listening conditions.

 

Words | Sentences | Digits | Melody | Instrument | Concatenated Sentence | Recognition Threshold

 

Group 1: Openset Word Recognition Training

This group uses Open-set Recognition Training Protocols. While this training group uses the same training materials (monosyllabic words) used in the closed-set phoneme recognition training, however, there is no explicit choice in this group. The user has to type the word or select the letter in the screen to have the words.. There are three training levels, including word recognition in quiet, in 10 dB SNR and in 0 dB SNR.

words

 

Group 2: Openset Sentence Recognition Training

This group uses Open-set Recognition Training Protocols. Same as openset word recognition training, the user has to type the whole sentence or click the letter in the screen to have the whole sentence. The program will compare the word in the sentence and determine the percentage points. Again, there are three training levels in this training groups, including quite, 10 dB, and 0 dB. The interface is same as the word group.

 

Group 3: Digits Recognition Training

This group uses both Open-set Recognition Training Protocols and Speech Synthesis based on Concatenation for assessing/training the listener's digits span, or their ability to recognize the number of digits. The number of digits per string ranges from 3 to 7 (3 digits, 5 digits, and 7 digits). Here shows the interface for this training group.

digits.

 

Group 4: Melody Notes Sequnece Recognition Training

This group uses both Open-set Recognition Training Protocols and Speech Synthesis based on Concatenation. This training group is to provide PIANO-based Melodic Sequence Recognition Training for CI patients to improve their abilities to recognize musical melodies, thereby improving their music appreciation. Different from MCI task, this is an openset recognition task. The sequence is random and has no particular pattern. Test stimuli were melodic sequences composed of 2, 3, 5, or 7 notes of equal duration whose frequencies corresponded to musical intervals. The note ranges from C4 to C5. Here shows the main interface for this group.

melody

 

Group 5: Intrument Sequence Recognition Training

This training group is to provide Instrument Sequence Recognition Training for CI patients to improve their abilities to recognize different musical instruments, thereby improving their music appreciation. Different from MCI task, this is an openset recognition task. The sequence is random and has no particular pattern. Test stimuli were melodic sequences composed of 2, 3, 5, or 7 notes of equal duration whose frequencies corresponded to musical intervals. This group uses both Open-set Recognition Training Protocols and Speech Synthesis based on Concatenation. Here shows the main interface for this group.

instrument

 

Group 6: Concatenated Sentence Recognition Training

This group uses Concatenated speech training protocols. The sentence includes five words as the following order: noun, verb, number, adj., and noun. Each cateagory includes 10 words, resulting in 100,000 random sentences. The user has to select the words from the screen (10x5) to have the whole sentence. The program will compare the whole sentnece and determine the percentage points. Again, there are three training levels in this training groups, including quite, 10 dB, and 0 dB. Here shows the interface for this training group.

Concatenated Sentence

 

Group 7: Speech Recognition Thresholds Training for Words, Sentences, Digit, and Concatenated Sentences

This group uses several Advanced Training Protocols, including Open-set Recognition Training Protocols, Speech Synthesis based on Concatenation, and Trial-based Adaptive Speech in Noise Training. The task in this group will assess/train the listener's ability to recognize words, sentences, or digits in the presence of background noise. The background will use six-talker speech babble. Speech recogition threshold, the signal-to-noise ratio that produces 50% of words, sentences or digits recognition, will be measured. The digit string has 3 digits. The main interface will be same as the above groups.