Page 1 / 3


open  

Introduction to Speech Processing

This is a collection of pedagogical material within the topic of speech and language technology. The idea is to provide teachers material for their courses, where they can pick and choose material which is appropriate for their own courses and self-study material on-line for anyone interested.

Authors:  Tom BäckströmOkko RäsänenAbraham ZewoudiePablo Pérez ZarazagaLiisa Koivusalo
Updated:  2022-01-27
Source:  https://wiki.aalto.fi/display/ITSP/Introduction+to+Speech+Processing
Keywords:  speechlanguagecommunicationeducationmachine-learningEnglish

open   documented  

Automatic Linguistic Unit Count Estimator (ALICE)

ALICE is a tool for estimating the number of adult-spoken linguistic units from child-centered audio recordings, as captured by microphones worn by children. It is meant as an open-source alternative for LENA adult word count (AWC) estimator.

Authors:  Okko RäsänenShreyas SeshadriMarvin LavechinAlejandrina CristiaMarisa Casillas
Updated:  2021-11-02
Source:  https://github.com/orasanen/ALICE
Keywords:  languagelinguisticsphoneticsspeech-productionArgentinian SpanishTseltalYélî DnyeEnglish

open  

Aphasia Games for Health

Building a gaming community for people with aphasia by supporting the development of games for recovery, providing resources for designers, and making aphasia friendly games accessible.

Authors:  William EvansJessica HammerKathryn HymesHakan SeyalıoğluMeguey BakerDeidra BrownJill VentricePatricia HanbridgeCarol Dow-RichardsClio Yun-su DavisSammie KimTim Hutchings
Updated:  2021-09-29
Source:  https://www.aphasiagamesforhealth.com/
Keywords:  languageaphasiaspeechreadingwritingEnglish

open  

The DLD Diagnostics Toolbox

The purpose of this toolbox is to address questions related to the diagnosis of Developmental Language Disorder (DLD).

Authors:  Lisa Archibald
Updated:  2021-07-06
Source:  https://www.uwo.ca/fhs/lwm/news/index.html
Keywords:  languagespeechdevelopmenteducationspeech-pathologyEnglish

open  

The Event Task Stimulus Set

The Event Task Stimulus Set was created to measure access to generalized events stored in semantic memory. It has been examined in a large normative sample as well as in people with neurological disorders (Dresang, Dickey, & Warren, 2020), and to measure semantic violations in visual processing (Proverbio & Riva, 2009).

Authors:  Federica RivaHaley C. DresangMichael Walsh DickeyTessa WarrenAlice Mado Proverbio
Updated:  2021-06-15
Source:  https://osf.io/pzqcj/
Keywords:  languagememorypsychologyaphasiaexperimentEnglish

open  

Global Signbank

Lexical database of Sign Language of the Netherlands (NGT).

Authors:  Onno CrasbornSteve Cassidy
Updated:  2021-04-29
Source:  https://signbank.cls.ru.nl/
Keywords:  languagemorphemehandshapesign-language-of-the-Netherlands

open  

childLex

childLex is based on a corpus of children’s books and comprises 10 million words that were syntactically annotated and lemmatized. childLex reports linguistic norms for lexical, superlexical, and sublexical variables in three different age groups: 6–8 (grades1–2), 9–10 (grades 3–4), and 11–12 years (grades 5–6).

Authors:  Sascha SchroederKay-Michael WürznerJulian HeisterAlexander GeykenReinhold Kliegl
Updated:  2021-03-02
Source:  https://osf.io/m59uv/
Keywords:  languagelexiconreading-developmentlinguisticsGerman

open  

Language History Questionnaire (version 3)

Language history questionnaire (LHQ) is an important tool for assessing language learners' linguistic background, the context and habits of language use, proficiency in multiple languages, and the dominance and cultural identity of the languages acquired.

Authors:  Ping LiSara SepanskiXiaowei ZhaoFan ZhangErlfang TsaiBrendan PulsAnya Yu
Updated:  2020-11-29
Source:  https://lhq3.herokuapp.com/
Keywords:  languagelinguisticsmultilinguialismeducation

open  

Corpus of Dutch Sign Language

The NGT is a collection data from deaf signers using Sign Language of the Netherlands (NGT).

Authors:  Onno CrasbornInge ZwitserloodJohan Ros
Updated:  2020-09-29
Source:  https://www.corpusngt.nl/
Keywords:  languagecommunicationDutch-Sign-Language

open   documented  

SemDis

SemDis uses advances in natural language processing to automatically determine how closely associated texts are to each other. Higher SemDis scores indicate two texts are less related, that is, they are more distantly related ideas or concepts.

Authors:  Dan Johnson & Roger Beaty
Updated:  2020-09-29
Source:  http://semdis.wlu.psu.edu/
Keywords:  languagesemanticsword-recognitionEnglish

open  

VietSLP

The San Diego State University Bilingual Development in Context research lab has created and validated a set of assessment tools for the Vietnamese language.

Authors:  Giang T. PhamQuynh DamKerry EbertBen PhamVan PhamHien HoangLinh PhamNgoc TranKristine Thuy DinhSon PhamThong LeChris Nguyen
Updated:  2020-09-29
Source:  https://vietslp.sdsu.edu/
Keywords:  speech-pathologylanguagebilingualVietnamese

open  

VL2 Storybook Apps

Stories told in sign language by fluent Deaf storytellers. Easy & accessible navigation designed for children. Page-by-page sign language videos supporting the printed sentences text. Rich interactive narrative with direct English to ASL vocabulary video translation. 120+ new vocabulary words with each app. Parents can learn new ASL signs along with their child.

Authors:  Motion Light Lab
Updated:  2020-09-29
Source:  https://vl2storybookapps.com/digital-library
Keywords:  languageeducationbilingualAmerican-Sign-LanguageEnglish

open  

The Internal Representations Questionnaire

The Internal Representations Questionnaire (IRQ) is a measure designed to quantify the subjective format of thought. There are four factors in the questionnaire namely; visual imagery, propensity to verbalize, representational manipulation and orthographic imagery.

Authors:  Hettie RoebuckPierce EdmistonGary Lupyan
Updated:  2020-07-14
Source:  https://osf.io/8rdzh/
Keywords:  psychologycognitionquestionnairelanguageEnglish

open  

The Model Talker System

The ModelTalker System converts plain English text to speech. It uses recorded speech (either from a prospective SGD user or from a voice donor chosen by or for the SGD user) to create a unique synthetic voice.

Authors:  H. Timothy BunnellJason LilleyMatthew BuzzellMaxwell SchmidBill MoyersDerek Freer
Updated:  2020-06-25
Source:  https://www.modeltalker.org/
Keywords:  languagecommunicationspeechphonologymorphologyEnglish

open  

Normative Data on Dutch Idiomatic Expressions

Normative data of 374 Dutch idiomatic expressions by 390 native speakers.

Authors:  Ferdy HubersCatia CucchiariniHelmer StrikTon Dijkstra
Updated:  2019-05-14
Source:  https://www.ru.nl/cls/publications/corpora/
Keywords:  languagespeechEnglishDutch

open  

Arizona Child Acoustic Database

The Arizona Child Acoustic Database is a longitudinal collection of audio samples from children between the ages of 2-7 years.

Authors:  Kate Bunton and Brad Story
Updated:  2018-06-20
Source:  https://repository.arizona.edu/handle/10150/316065
Keywords:  languagespeech-developmentacousticslinguisticsEnglish

open  

BilingBank

BilingBank is a component of TalkBank dedicated to providing corpora for the study of multilingualism.

Authors:  Brian MacWhinney
Updated:  2018-05-04
Source:  https://biling.talkbank.org/
Keywords:  bilingualmultilingualismlanguagecommunicationEnglish

open  

Nijmegen Corpus of Spanish English

Around 38 hours of high-quality recordings featuring 34 Spanish speakers from Madrid talking in English to two Dutch confederates, in an informal and in a formal setting.

Authors:  Mirjam ErnestusHuib Kouwenhoven
Updated:  2018-04-06
Source:  https://mirjamernestus.nl/Ernestus/NCSE/index.php
Keywords:  languagecommunicationspeechEnglish

open   documented  

Combinatorial Expressive Speech Engine

C.L.E.E.S.E. (Combinatorial Expressive Speech Engine) is a tool designed to generate an infinite number of natural-sounding, expressive variations around an original speech recording.

Authors:  Juan José BurredEmmanuel Ponsot
Updated:  2018-03-29
Source:  http://cream.ircam.fr/?p=521
Keywords:  languagespeechpitchFrenchEnglishJapanese

open   documented  

ANGUS

ANGUS is a real-time voice transformation tool able to simulate cues of arousal/roughness on arbitrary voice signals with a high degree of realism.

Authors:  Marco LiuniLuc Ardaillon
Updated:  2018-03-07
Source:  http://cream.ircam.fr/?p=787
Keywords:  languagevoicevocal-tractEnglish

Page 1 / 3