Réseau de neurones à propagation avantUn réseau de neurones à propagation avant, en anglais feedforward neural network, est un réseau de neurones artificiels acyclique, se distinguant ainsi des réseaux de neurones récurrents. Le plus connu est le perceptron multicouche qui est une extension du premier réseau de neurones artificiel, le perceptron inventé en 1957 par Frank Rosenblatt. vignette|Réseau de neurones à propagation avant Le réseau de neurones à propagation avant est le premier type de réseau neuronal artificiel conçu. C'est aussi le plus simple.
Production de la paroleLa production de la parole est un processus qui transforme les pensées en parole. Cette activité comprend la sélection des mots, l'organisation des formes grammaticales pertinentes et l'articulation des sons par le système moteur via l'appareil vocal. Cette production peut être spontanée (par exemple, quand une personne prononce des mots lors d'une conversation), réactive (par exemple, quand elle identifie une illustration ou qu'elle fait une lecture à voix haute) ou imitative (quand elle répète les mots qu'une autre personne a dits).
Time delay neural networkTime delay neural network (TDNN) is a multilayer artificial neural network architecture whose purpose is to 1) classify patterns with shift-invariance, and 2) model context at each layer of the network. Shift-invariant classification means that the classifier does not require explicit segmentation prior to classification. For the classification of a temporal pattern (such as speech), the TDNN thus avoids having to determine the beginning and end points of sounds before classifying them.
Speech repetitionSpeech repetition occurs when individuals speak the sounds that they have heard another person pronounce or say. In other words, it is the saying by one individual of the spoken vocalizations made by another individual. Speech repetition requires the person repeating the utterance to have the ability to map the sounds that they hear from the other person's oral pronunciation to similar places and manners of articulation in their own vocal tract.
Speech codingSpeech coding is an application of data compression to digital audio signals containing speech. Speech coding uses speech-specific parameter estimation using audio signal processing techniques to model the speech signal, combined with generic data compression algorithms to represent the resulting modeled parameters in a compact bitstream. Common applications of speech coding are mobile telephony and voice over IP (VoIP).
PerceptionLa perception est l'activité par laquelle un sujet fait l'expérience d'objets ou de propriétés présents dans son environnement. Cette activité repose habituellement sur des informations fournies par ses sens. Chez l'espèce humaine, la perception est aussi liée aux mécanismes de cognition. Le mot « perception » désigne : soit le processus de recueil et de traitement de l'information sensorielle ou sensible (en psychologie cognitive par exemple) ; soit la prise de conscience qui en résulte (en philosophie de la perception notamment).
Neural networkA neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.
Long short-term memoryLong short-term memory (LSTM) network is a recurrent neural network (RNN), aimed to deal with the vanishing gradient problem present in traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, hidden Markov models and other sequence learning methods. It aims to provide a short-term memory for RNN that can last thousands of timesteps, thus "long short-term memory".
Audio deepfakeAn audio deepfake (also known as voice cloning) is a type of artificial intelligence used to create convincing speech sentences that sound like specific people saying things they did not say. This technology was initially developed for various applications to improve human life. For example, it can be used to produce audiobooks, and also to help people who have lost their voices (due to throat disease or other medical problems) to get them back. Commercially, it has opened the door to several opportunities.
Language processing in the brainIn psycholinguistics, language processing refers to the way humans use words to communicate ideas and feelings, and how such communications are processed and understood. Language processing is considered to be a uniquely human ability that is not produced with the same grammatical understanding or systematicity in even human's closest primate relatives. Throughout the 20th century the dominant model for language processing in the brain was the Geschwind-Lichteim-Wernicke model, which is based primarily on the analysis of brain-damaged patients.