AIMC Topic: Speech

Clear Filters Showing 311 to 320 of 395 articles

Minimalistic toy robot to analyze a scenery of speaker-listener condition in autism.

Cognitive processing
Atypical neural architecture causes impairment in communication capabilities and reduces the ability of representing the referential statements of other people in children with autism. During a scenery of "speaker-listener" communication, we have ana...

Machine learning based sample extraction for automatic speech recognition using dialectal Assamese speech.

Neural networks : the official journal of the International Neural Network Society
Automatic Speaker Recognition (ASR) and related issues are continuously evolving as inseparable elements of Human Computer Interaction (HCI). With assimilation of emerging concepts like big data and Internet of Things (IoT) as extended elements of HC...

Classifier Subset Selection for the Stacked Generalization Method Applied to Emotion Recognition in Speech.

Sensors (Basel, Switzerland)
In this paper, a new supervised classification paradigm, called classifier subset selection for stacked generalization (CSS stacking), is presented to deal with speech emotion recognition. The new approach consists of an improvement of a bi-level mul...

Deep Neural Networks with Multistate Activation Functions.

Computational intelligence and neuroscience
We propose multistate activation functions (MSAFs) for deep neural networks (DNNs). These MSAFs are new kinds of activation functions which are capable of representing more than two states, including the N-order MSAFs and the symmetrical MSAF. DNNs w...

Augmented Robotics Dialog System for Enhancing Human-Robot Interaction.

Sensors (Basel, Switzerland)
Augmented reality, augmented television and second screen are cutting edge technologies that provide end users extra and enhanced information related to certain events in real time. This enriched information helps users better understand such events,...

Low-dimensional recurrent neural network-based Kalman filter for speech enhancement.

Neural networks : the official journal of the International Neural Network Society
This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the pro...

A Digital Liquid State Machine With Biologically Inspired Learning and Its Application to Speech Recognition.

IEEE transactions on neural networks and learning systems
This paper presents a bioinspired digital liquid-state machine (LSM) for low-power very-large-scale-integration (VLSI)-based machine learning applications. To the best of the authors' knowledge, this is the first work that employs a bioinspired spike...

Deep Convolutional Neural Networks for large-scale speech tasks.

Neural networks : the official journal of the International Neural Network Society
Convolutional Neural Networks (CNNs) are an alternative type of neural network that can be used to reduce spectral variations and model spectral correlations which exist in signals. Since speech signals exhibit both of these properties, we hypothesiz...

Frame-by-frame language identification in short utterances using deep neural networks.

Neural networks : the official journal of the International Neural Network Society
This work addresses the use of deep neural networks (DNNs) in automatic language identification (LID) focused on short test utterances. Motivated by their recent success in acoustic modelling for speech recognition, we adapt DNNs to the problem of id...

Working Memory and Self-Directed Inner Speech Enhance Multitask Generalization in Active Inference.

Neural computation
This simulation study shows how a set of working memory tasks can be acquired simultaneously through interaction between a stacked recurrent neural network (RNN) and multiple working memories. In these tasks, temporal patterns are provided, followed ...