Results 101 to 110 of about 1,664 (139)

Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

IEEE Transactions on Audio, Speech, and Language Processing, 2023
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called VALL-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a ...
Chengyi Wang, Sanyuan Chen, Yu Wu, Zi-Hua Zhang, Long Zhou, Shujie Liu, Zhuo Chen, Yanqing Liu, Huaming Wang, Jinyu Li, Lei He, Sheng Zhao, Furu Wei   +12 more
semanticscholar   +1 more source

Unsupervised, Semi-Supervised and LLM-Based Morphological Segmentation for Bribri

Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
Morphological Segmentation is a major task in Indigenous language documentation. In this paper we introduce a novel statistical algorithm called Morphemo to split words into their constituent morphemes, and we compare its performance to five other ...
Carter Anderson, Mien Nguyen, Rolando Coto-Solano   +2 more
semanticscholar   +1 more source

Noun Incorporation in Bribri

International Journal of American Linguistics
 Offer a preliminary description of the ‘productive’ phenomenon of Noun Incorporation (NI) in Bribri, a Chibchan language spoken in Costa Rica by approximately 10.000 people.
Sara Pacchiarotti
semanticscholar   +1 more source

Diacritic Restoration for Low-Resource Indigenous Languages: Case Study with Bribri and Cook Islands Māori

arXiv.org
We present experiments on diacritic restoration, a form of text normalization essential for natural language processing (NLP) tasks. Our study focuses on two extremely under-resourced languages: Bribri, a Chibchan language spoken in Costa Rica, and Cook ...
Rolando Coto-Solano, Daisy Li, Manoela Teleginski Ferraz, Olivia Sasse, Cha Krupka, Sharid Lo'aiciga, Sally Akevai Nicholas   +6 more
semanticscholar   +1 more source

Morphological Tagging in Bribri Using Universal Dependency Features

AMERICASNLP
This paper outlines the Universal Features tagging of a dependency treebank for Bribri, an Indigenous language of Costa Rica. Universal Features are a morphosyntactic tagging component of Universal Dependencies, which is a framework that aims to provide ...
Jessica Karson, Rolando Coto-Solano
semanticscholar   +1 more source

JHU’s Submission to the AmericasNLP 2025 Shared Task on the Creation of Educational Materials for Indigenous Languages

Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
This paper presents JHU’s submission to the AmericasNLP shared task on the creation of educational materials for Indigenous languages. The task involves transforming a base sentence given one or more tags that correspond to grammatical features, such as ...
Tom Lupicki, Lavanya Shankar, Kaavya Chaparala, David Yarowsky   +3 more
semanticscholar   +1 more source

REVITALIZATION OR RECLAMATION? REFRAMING THE RECOVERY OF INDIGENOUS LANGUAGES IN LATIN AMERICA: A HISTORICAL AND AIDRIVEN APPROACH

International Journal of Language, Linguistics, Literature and Culture
Indigenous languages of Latin America have faced significant decline due to colonization, globalization, and sociopolitical factors. While some languages remain endangered, others have entirely disappeared, leaving behind limited historical records or ...
Dianala M. Bernard, Maren A. Benn
semanticscholar   +1 more source