Double-vowel segregation through temporal correlation: a bio-inspired neural network paradigm
نویسندگان
چکیده
A two-layer spiking neural network is used to segregate double vowels. The first layer is a partially connected spiking neurons of relaxation oscillatory type, while the second layer consists of fully connected relaxation oscillators. A twodimensional auditory image generated by the enhanced spectrum of cochlear filter bank envelopes is computed. The segregation is based on a channel selection strategy. At each instant of time each channel is assigned to one of the sources present in the auditory scene, i.e. speakers. No prior estimation of pitch for the underlying sources is necessary. Index Terms – Computational Auditory Scene Analysis (CASA), bio-inspired neural networks, sound segregation, cochleotopic/AMtopic map (CAM), temporal binding.
منابع مشابه
Binding of Audio Elements in the Sound Source Segregation Problem via a Two-layered Bio-inspired Neural Network
We use a two-layered bio-inspired neural network to segregate sound sources, i.e. double-vowels or intruding noises in speech. The architecture of the network consists of spiking neurons. The spiking neurons in both layers are modelized by relaxation oscillators. The first layer of the network is locally connected, while the second layer is a fully connected network. Our auditory image is based...
متن کاملمعرفی شبکه های عصبی پیمانه ای عمیق با ساختار فضایی-زمانی دوگانه جهت بهبود بازشناسی گفتار پیوسته فارسی
In this article, growable deep modular neural networks for continuous speech recognition are introduced. These networks can be grown to implement the spatio-temporal information of the frame sequences at their input layer as well as their labels at the output layer at the same time. The trained neural network with such double spatio-temporal association structure can learn the phonetic sequence...
متن کاملDouble-vowel Segregation based on a Cochleotopic/AMtopic Map using a Biological Neural Network
We propose an auditory scene analyzer for double vowel segregation. Our technique is based on a two-dimensional representation of the signal that generates a cochleotoptic/AMtopic map, which is used to mimic the periodicity analysis performed in the principal monaural pathway at the brain-stem level. In our scheme, the incoming signal is first processed by a cochlear filter bank and the AM modu...
متن کاملمشکلات جداسازی اصوات گفتاری همزمان در کودکان کم شنوا
Objective: This study was a basic investigation of the ability of concurrent speech segregation in hearing impaired children. Concurrent segregation is one of the fundamental components of auditory scene analysis and plays an important role in speech perception. In the present study, we compared auditory late responses or ALRs between hearing impaired and normal children. Materials & Methods...
متن کاملExploiting Natural Asynchrony and Local Knowledge within Systemic Computation to Enable Generic Neural Structures
Bio-inspired processes are involved more and more in today’s technologies, yet their modelling and implementation tend to be taken away from their original concept because of the limitations of the classical computation paradigm. To address this, [1] introduced systemic computation (SC), a model of interacting systems with natural characteristics, and [2] introduced a modelling platform with a ...
متن کامل