Speech synthesisSpeech synthesis is the artificial production of human speech. A computer system used for this purpose is called a speech synthesizer, and can be implemented in software or hardware products. A text-to-speech (TTS) system converts normal language text into speech; other systems render symbolic linguistic representations like phonetic transcriptions into speech. The reverse process is speech recognition. Synthesized speech can be created by concatenating pieces of recorded speech that are stored in a database.
Types of artificial neural networksThere are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.
Unsupervised learningUnsupervised learning, is paradigm in machine learning where, in contrast to supervised learning and semi-supervised learning, algorithms learn patterns exclusively from unlabeled data. Neural network tasks are often categorized as discriminative (recognition) or generative (imagination). Often but not always, discriminative tasks use supervised methods and generative tasks use unsupervised (see Venn diagram); however, the separation is very hazy. For example, object recognition favors supervised learning but unsupervised learning can also cluster objects into groups.
Language acquisitionLanguage acquisition is the process by which humans acquire the capacity to perceive and comprehend language (in other words, gain the ability to be aware of language and to understand it), as well as to produce and use words and sentences to communicate. Language acquisition involves structures, rules, and representation. The capacity to use language successfully requires one to acquire a range of tools including phonology, morphology, syntax, semantics, and an extensive vocabulary.
Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Language educationLanguage education – the process and practice of teaching a second or foreign language – is primarily a branch of applied linguistics, but can be an interdisciplinary field. There are four main learning categories for language education: communicative competencies, proficiencies, cross-cultural experiences, and multiple literacies. Increasing globalization has created a great need for people in the workforce who can communicate in multiple languages.
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Evolutionary psychology of languageEvolutionary psychology of language is the study of the evolutionary history of language as a psychological faculty within the discipline of evolutionary psychology. It makes the assumption that language is the result of a Darwinian adaptation. There are many competing theories of how language might have evolved, if indeed it is an evolutionary adaptation. They stem from the belief that language development could result from an adaptation, an exaptation, or a by-product. Genetics also influence the study of the evolution of language.
Origin of languageThe origin of language (spoken and signed, as well as language-related technological systems such as writing), its relationship with human evolution, and its consequences have been subjects of study for centuries. Scholars wishing to study the origins of language must draw inferences from evidence such as the fossil record, archaeological evidence, contemporary language diversity, studies of language acquisition, and comparisons between human language and systems of communication existing among animals (particularly other primates).
Cache language modelA cache language model is a type of statistical language model. These occur in the natural language processing subfield of computer science and assign probabilities to given sequences of words by means of a probability distribution. Statistical language models are key components of speech recognition systems and of many machine translation systems: they tell such systems which possible output word sequences are probable and which are improbable.
Neural machine translationNeural machine translation (NMT) is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model. They require only a fraction of the memory needed by traditional statistical machine translation (SMT) models. Furthermore, unlike conventional translation systems, all parts of the neural translation model are trained jointly (end-to-end) to maximize the translation performance.
Queer studiesQueer studies, sexual diversity studies, or LGBT studies is the study of topics relating to sexual orientation and gender identity usually focusing on lesbian, gay, bisexual, transgender, gender dysphoria, asexual, queer, questioning, intersex people and cultures. Originally centered on LGBT history and literary theory, the field has expanded to include the academic study of issues raised in archaeology, sociology, psychiatry, anthropology, the history of science, philosophy, psychology, sexology, political science, ethics, and other fields by an examination of the identity, lives, history, and perception of being queer.
Women's studiesWomen's studies is an academic field that draws on feminist and interdisciplinary methods to place women's lives and experiences at the center of study, while examining social and cultural constructs of gender; systems of privilege and oppression; and the relationships between power and gender as they intersect with other identities and social locations such as race, sexual orientation, socio-economic class, and disability.
Gender studiesGender studies is an interdisciplinary academic field devoted to analysing gender identity and gendered representation. Gender studies originated in the field of women's studies, concerning women, feminism, gender, and politics. The field now overlaps with queer studies and men's studies. Its rise to prominence, especially in Western universities after 1990, coincided with the rise of deconstruction.
Media studiesMedia studies is a discipline and field of study that deals with the content, history, and effects of various media; in particular, the mass media. Media Studies may draw on traditions from both the social sciences and the humanities, but mostly from its core disciplines of mass communication, communication, communication sciences, and communication studies.
