Human Language Technology Laboratory

Human Language Technology Laboratory This strongly multidisciplinar INESC-ID lab brings together people who work in Human Language Techno

The Human Language Technology laboratory, as a congregation of people working on human language technology and related matters, is the natural evolution of the Spoken Language Systems Laboratory (L²F), a laboratory created in 2001, to bring together several research groups of INESC and independent researchers to contribute to the area of computational processing of spoken language for European Por

tuguese. The long term goal of L²F was to bridge the gap between natural spoken language and the underlying semantic information. The HLT laboratory includes researchers/faculty from various universities, as well as graduate and post-graduate researchers. Their background ranges from Electrical Engineering, to Computer Science, and Linguistics. This strongly interdisciplinary group is actively involved in many areas of language research and development, both spoken and written, including, without limitation, speech recognition, speech synthesis, speech coding, speech understanding, audio indexing, multimodal dialogue systems, language and dialect identification, speech-to-speech machine translation, automatic summarization, natural language database interfaces, natural language generation, text simplification, named entity recognition, question answering, among others and in no particular order.

2024 Christmas Dinner!
18/12/2024

2024 Christmas Dinner!

Congratulations to HLT researchers Catarina, Alberto, and Isabel, for their publication “Speech as a Biomarker for Disea...
18/12/2024

Congratulations to HLT researchers Catarina, Alberto, and Isabel, for their publication “Speech as a Biomarker for Disease Detection”!

Congratulations to our researchers John and Isabel, for their publication “SODA-EVAL: Open-Domain Dialogue Evaluation in...
22/11/2024

Congratulations to our researchers John and Isabel, for their publication “SODA-EVAL: Open-Domain Dialogue Evaluation in the age of LLMs” in EMNLP’24 in Miami, Florida, USA!

Congratulations Catarina, for your PhD thesis defence on Nov. 18th! Catarina’s thesis explores the multifaceted role of ...
21/11/2024

Congratulations Catarina, for your PhD thesis defence on Nov. 18th! Catarina’s thesis explores the multifaceted role of speech as a biomarker for detecting neurodegenerative, psychiatric, and respiratory diseases. It highlights novel and complementary modalities, such as EMG and visual speech, addresses challenges in the field that underscore the need for responsible research, and explores interpretable models for reference speech characterization and disease detection. Additionally, it investigates the potential of large language models (LLMs) to enhance disease detection.

Exciting news from IberSpeech 2024! The Inesc-ID (HLT) team proudly represented the Accelerat.AI project, showcasing our...
18/11/2024

Exciting news from IberSpeech 2024! The Inesc-ID (HLT) team proudly represented the Accelerat.AI project, showcasing our latest advancements in human language technology. It was a fantastic opportunity to connect with fellow researchers and industry leaders, share insights, and explore the future of AI in speech processing.

Our researchers Catarina Botelho and Alberto Abad are giving a talk today in the context of Deep Learning Sessions Portu...
08/02/2024

Our researchers Catarina Botelho and Alberto Abad are giving a talk today in the context of Deep Learning Sessions Portugal. You can watch the talk online for free by registering in the event (https://lnkd.in/exSrJqhW).

Explore the profound impact of deep learning on speech research with Catarina and Alberto. Learn about off-the-shelf tools, challenges, and open problems driving current research. Delve into the dual nature of speech, covering linguistic content, paralinguistic information, and its potential in medical diagnosis.

A dor crónica é uma realidade para mais de 30% da população portuguesa, persistindo por pelo menos três meses e, muitas ...
24/04/2023

A dor crónica é uma realidade para mais de 30% da população portuguesa, persistindo por pelo menos três meses e, muitas vezes, estendendo-se durante anos. Para aqueles que nunca sofreram de dor crónica, é difícil entender a sensação de isolamento e falta de compreensão que os pacientes sentem diariamente.

Diogo Nunes, estudante de doutoramento do InescID, está a trabalhar na análise da linguagem da dor para que possa ser entendida por todos. O objetivo final é ajudar as pessoas que sofrem de dor crónica a entender melhor a sua situação. No futuro, espera-se desenvolver uma aplicação que permita aos médicos e pacientes ter acesso a métricas importantes para o tratamento da dor crónica.

O Público está a promover o “Conta-nos a tua ciência”, convidando alunos de doutoramento da ULisboa a partilhar com os leitores do Público um pequeno texto sobre a sua investigação.

https://www.publico.pt/2023/04/22/ciencia/noticia/garantidamente-ja-sentimos-dor-fisica-2046798

Diogo Nunes has been awarded the “Best Clinical Scientific Article” Prize by Associação Portuguesa para o Estudo da Dor ...
21/11/2022

Diogo Nunes has been awarded the “Best Clinical Scientific Article” Prize by Associação Portuguesa para o Estudo da Dor (the Portuguese Association for the Study of Pain). On being awarded the prize, Diogo commented that “Our mission is to study the verbal expression of pain and to take advantage of that knowledge in order to help those that suffer from chronic pain. I am very happy with this award, because it is an important recognition of the clinical valence of the work we have been doing and of the impact it can have.”

Catarina Botelho has been awarded the Maria de Lourdes Pintasilgo Award in the “Young Alumna” category. Catarina's PhD w...
18/11/2022

Catarina Botelho has been awarded the Maria de Lourdes Pintasilgo Award in the “Young Alumna” category. Catarina's PhD work concerns the use of speech as a biomarker for speech affecting diseases.

Our colleague Fernando Batista spoke with Dalila Carvalho, from Antena 2, about natural language technologies: transform...
18/11/2022

Our colleague Fernando Batista spoke with Dalila Carvalho, from Antena 2, about natural language technologies: transformers, language in social networks, and other human-machine interaction through speech. The full episodes are available here: https://www.rtp.pt/play/p8296/palavras-cruzadas

Gonçalo is our new PhD student in the MAIA project.
19/02/2021

Gonçalo is our new PhD student in the MAIA project.

Conheça os novos projetos de Afonso e Gonçalo Raposo, antigos bolseiros Gulbenkian Mais, que começam este ano os doutoramentos em Engenharia Biomédica e Informática.

Endereço

Rua Alves Redol 9
Lisbon
1000-029LISBOA

Horário de Funcionamento

Segunda-feira 10:00 - 17:00
Terça-feira 10:00 - 18:00
Quarta-feira 10:00 - 18:00
Quinta-feira 10:00 - 18:00
Sexta-feira 10:00 - 18:00

Telefone

+351213100313

Notificações

Seja o primeiro a receber as novidades e deixe-nos enviar-lhe um email quando Human Language Technology Laboratory publica notícias e promoções. O seu endereço de email não será utilizado para qualquer outro propósito, e pode cancelar a subscrição a qualquer momento.

Compartilhar