Publication

On Compressibility of Neural Network phonological Features for Low Bit Rate Speech Coding

Related concepts (40)

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.

Distinctive feature

In linguistics, a distinctive feature is the most basic unit of phonological structure that distinguishes one sound from another within a language. For example, the feature [voice] distinguishes the two bilabial plosives: [p] and [b]. There are many different ways of defining and arranging features into feature systems: some deal with only one language while others are developed to apply to all languages. Distinctive features are grouped into categories according to the natural classes of segments they describe: major class features, laryngeal features, manner features, and place features.

Phonetic transcription

Phonetic transcription (also known as phonetic script or phonetic notation) is the visual representation of speech sounds (or phones) by means of symbols. The most common type of phonetic transcription uses a phonetic alphabet, such as the International Phonetic Alphabet. The pronunciation of words in all languages changes over time. However, their written forms (orthography) are often not modified to take account of such changes, and do not accurately represent the pronunciation.

Error correction code

In computing, telecommunication, information theory, and coding theory, forward error correction (FEC) or channel coding is a technique used for controlling errors in data transmission over unreliable or noisy communication channels. The central idea is that the sender encodes the message in a redundant way, most often by using an error correction code or error correcting code (ECC). The redundancy allows the receiver not only to detect errors that may occur anywhere in the message, but often to correct a limited number of errors.

Vocoder

A vocoder (ˈvoʊkoʊdər, a portmanteau of voice and encoder) is a category of speech coding that analyzes and synthesizes the human voice signal for audio data compression, multiplexing, voice encryption or voice transformation. The vocoder was invented in 1938 by Homer Dudley at Bell Labs as a means of synthesizing human speech. This work was developed into the channel vocoder which was used as a voice codec for telecommunications for speech coding to conserve bandwidth in transmission.

Phonology

Phonology is the branch of linguistics that studies how languages or dialects systematically organize their phones or, for sign languages, their constituent parts of signs. The term can also refer specifically to the sound or sign system of a particular language variety. At one time, the study of phonology related only to the study of the systems of phonemes in spoken languages, but may now relate to any linguistic analysis either: Sign languages have a phonological system equivalent to the system of sounds in spoken languages.

Speech perception

Speech perception is the process by which the sounds of language are heard, interpreted, and understood. The study of speech perception is closely linked to the fields of phonology and phonetics in linguistics and cognitive psychology and perception in psychology. Research in speech perception seeks to understand how human listeners recognize speech sounds and use this information to understand spoken language.

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.

Two-streams hypothesis

The two-streams hypothesis is a model of the neural processing of vision as well as hearing. The hypothesis, given its initial characterisation in a paper by David Milner and Melvyn A. Goodale in 1992, argues that humans possess two distinct visual systems. Recently there seems to be evidence of two distinct auditory systems as well. As visual information exits the occipital lobe, and as sound leaves the phonological network, it follows two main pathways, or "streams".

Low-density parity-check code

In information theory, a low-density parity-check (LDPC) code is a linear error correcting code, a method of transmitting a message over a noisy transmission channel. An LDPC code is constructed using a sparse Tanner graph (subclass of the bipartite graph). LDPC codes are , which means that practical constructions exist that allow the noise threshold to be set very close to the theoretical maximum (the Shannon limit) for a symmetric memoryless channel.

Line code

In telecommunication, a line code is a pattern of voltage, current, or photons used to represent digital data transmitted down a communication channel or written to a storage medium. This repertoire of signals is usually called a constrained code in data storage systems. Some signals are more prone to error than others as the physics of the communication channel or storage medium constrains the repertoire of signals that can be used reliably. Common line encodings are unipolar, polar, bipolar, and Manchester code.