Sound Express Basic Module:

This installation program will install the basic version of Sound Express, which include one basic module called Sound Express: Basic Edition. This basic module contains seven training groups, including 1) Pure Tones – practice identifying different pitches of sound; 2) Environment Sounds – practice identifying common environment sounds; 3) Male/Female Identification - practice discrimination between speakers; 4) Vowel Recognition - practice vowel discrimination and identification; 5) Consonant Recognition - practice consonant discrimination and identification; 6) Word Discrimination – practice common words from four different topic categories; 7) Everyday Sentences – practice identifying sentences with different levels of background noise; 8) Music Appreciation – practice identifying musical instruments and familiar tunes as a start to music appreciation.

More >>>

This advanced module is to provide MIDI-based Melodic Contour Identification Training for CI patients to improve their abilities to recognize musical melodies, thereby improving their music appreciation. For the MCI task, test stimuli were melodic contours composed of 5 notes of equal duration whose frequencies corresponded to musical intervals. Intruments include 1) Pure Tones; 2) Piano Stimuli; 3) Trumpet Stimuli; 4) Violin Stimuli; 5) Organ Stimuli; 6) Clarinet Stimuli; 7) Glockenspiel Stimuli;

There are 4 training levels for each instrument, including 1) Level 1: note patterns with 5-6 semitone difference; 2) Level 2: note patterns with 3-4 semitone difference; 3) Level 3: note patterns with 2 semitone difference; 4) Level 4: note patterns with 1 semitone difference.

More >>>

The basic module in the Sound Express provides only the closed-set training protocol. The number of alternative-choices is fixed for each training session and the targeted word is one of the alternative choices. One key feature developed in Sound Express is the OPEN-SET style training protocols. The user has to type in the words or others after the presentations of acoustic stimuli. The training includes the following training groups: 1) Monosyllabic words (quiet, 10dB, 0 dB) with speech babbles; 2) Everyday sentences (quiet, 10dB, 0dB); 3) Randomly generated Digits (3, 5, 7 digits); 4) Randomly generated melodic sequences (2, 3, and 5 notes); 5) Randomly generated instrument sequences (2, 3, and 5 instruments); 6) Recognition threshold (words, sentences, 3 digits) with speech babble;

Advanced Training Protocols used 1) Open-set Recognition Training Protocols; 2) Speech Synthesis based on Concatenation.; 3) Trial-based Adaptive Speech in Noise Training.

More >>>

The basic module in the Sound Express mainly provides speech recognition training in quiet listening conditions. However, most CI users performed much worse in the difficult listening conditions. This advanced module provides adaptive speech in noise training to improve speech perception in noisy environment. The training includes the following training groups: 1) Medial Vowel Contrast Training in Noise with Monosyllabic Words. 2) Initial Consonant Contrast Training in Noise with Monosyllabic Words. 3) Medial Consonant Contrast Training in Noise with Monosyllabic Words. 4) Final Consonant Contrast Training in Noise with Monosyllabic Words. 5) Number Training in Noise. 6) Everyday Sentences Training in Noise. Three kinds of background noise are used, including 1) Six-talker speech babble; 2) Low-pass noise; 3) White noise.

More >>

The basic module in the Sound Express mainly provides broadband speech recognition training in quiet listening conditions. Studies have shown that most CI users' recognition performance, especially consonant and sentence recognition scores, dropped significantly with reduced bandwidth, which often occurred during telephone conversation. This advanced module provides telephone speech training to improve speech perception in limited bandwidth. The training groups are same as those used in the basic training module except that the speech materials are bandlimited to 300-3200 Hz in real time in this module.

More >>