Publication

End-to-End Acoustic Modeling using Convolutional Neural Networks for HMM-based Automatic Speech Recognition

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Concepts related to End-to-End Acoustic Modeling using Convolutional Neural Networks for HMM-based Automatic Speech Recognition | EPFL Graph Search

Feedforward neural network

A feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.

Speech production

Speech production is the process by which thoughts are translated into speech. This includes the selection of words, the organization of relevant grammatical forms, and then the articulation of the resulting sounds by the motor system using the vocal apparatus. Speech production can be spontaneous such as when a person creates the words of a conversation, reactive such as when they name a picture or read aloud a written word, or imitative, such as in speech repetition.

Time delay neural network

Time 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 repetition

Speech 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 coding

Speech 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).

Perception

Perception () is the organization, identification, and interpretation of sensory information in order to represent and understand the presented information or environment. All perception involves signals that go through the nervous system, which in turn result from physical or chemical stimulation of the sensory system. Vision involves light striking the retina of the eye; smell is mediated by odor molecules; and hearing involves pressure waves.

Neural network

A 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 memory

Long 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 deepfake

An 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 brain

In 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.