An SOM-based auditory memory model that learns to perform auditory expectation in an unsupervised manner
Date Issued
2004
Date
2004
Author(s)
Li, Wu-Hsi
DOI
en-US
Abstract
We propose an unsupervised auditory memory model which learns a basic form of auditory knowledge – “what usually happens in sequence” of the audio signal. We use a self-organizing map in the bottom layer of the model; each neuron on the map reacts to specific acoustic feature. The input signal is mapping on the acoustic feature map; a series of neuron is activated in sequence as a result. Then the memory model gains auditory knowledge in an indirect way: it observes the map and learns the sequential regularities of the neuron activities. The model has a context buffer, which keeps the information of previous activated neurons. It uses the context information and the statistic regularities it has learned to anticipate the next active neuron. Since each neuron maps to specific acoustic feature, the prediction of which neuron to be activated is like to expect the sound to hear. Compare what actually happens with what the model expects to happen: When the model makes a correct prediction of the active neuron, the sound it hears is expected. In contrast, when the model makes a wrong prediction, the sound it hears is unexpected. The information of whether the input signal is expected or unexpected provides clues for further perception process. For example, the model can use these information to segment the signal into sound units. Moreover, we can estimate the information quantity given by each short-time frame of signal. Experiment on speech and music signal are conducted to demonstrate how our model learns to expect what it hears.
Subjects
自我組織圖
聽覺預期
聽覺記憶
redundancy
auditory memory
auditory expectation
self-organizing map
sequence learning
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-93-R91921093-1.pdf
Size
23.31 KB
Format
Adobe PDF
Checksum
(MD5):739f304c3682803dc06db7a5680c30ea