Challenge: Existing research on speech synthesis systems for three Indigenous languages in Canada requires tens of hours of audio recordings to be trained.
Approach: They build a system for three Indigenous languages spoken in Canada using 1 hour of training data and 10 hours of data to train low-resource models.
Outcome: The proposed system can produce speech with comparable naturalness to a Tacotron2 model trained with 10 hours of data.

Similar Papers

Not always about you: Prioritizing community needs when developing endangered language technology (2022.acl-long)

Copied to clipboard

Challenge: low-resource languages lack the quantity of data needed to train statistical and machine learning tools and models.
Approach: They propose to use language technology to support endangered languages' revitalization . they propose to work with indigenous speakers to develop technology for such training .
Outcome: The authors discuss the challenges that researchers and indigenous speech community members face when working together to develop language technology to support endangered languages.
Developing multilingual speech synthesis system for Ojibwe, Mi’kmaq, and Maliseet (2025.naacl-short)

Copied to clipboard

Challenge: In general, speech synthesis for Indigenous languages is underdeveloped compared to the majority of languages.
Approach: They propose to train a multilingual model on three typologically similar languages to improve performance over monolingual models.
Outcome: The proposed model can train on three similar languages with high performance and is highly competitive with self-attention architectures with higher memory efficiency.
Indigenous language technologies in Canada: Assessment, challenges, and successes (C18-1)

Copied to clipboard

Challenge: There are approximately 60 Indigenous languages currently spoken in Canada.
Approach: They examine which technologies have been developed and which are feasible to develop for the 60 Indigenous languages spoken in Canada.
Outcome: The proposed technologies are based on the existing technologies and are feasible for most or all of these languages.
Thesis Proposal: Development of End-to-End Speech Translation Models for Indian Languages (2026.eacl-srw)

Copied to clipboard

Challenge: Existing approaches to speech-to-speech translation rely on cascaded pipelines . current approaches rely only on text representations, but they suffer from errors and latency . a new direct speech translation framework is proposed to bridge linguistic gaps .
Approach: They propose a sequence-to-sequence direct speech translation framework that can translate speech from one Indian language to another without relying on intermediate text representations.
Outcome: The proposed framework can translate speech from one Indian language to another without relying on intermediate text representations.
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2021.naacl-main)

Copied to clipboard

Challenge: a growing body of work is focused on improving performance in low-resource settings . a goal of this study is to explain how these methods differ in their requirements .
Approach: They propose to analyze data-lean scenarios across different dimensions of data availability to understand which approaches are effective in a specific low-resource setting.
Outcome: The proposed methods enable learning when training data is sparse.
On Generative Spoken Language Modeling from Raw Audio (2021.tacl-1)

Copied to clipboard

Challenge: Using a set of metrics to evaluate the learned representations, we aim to create a system that learns from natural interactions as infants learn their first language.
Approach: They propose a task of learning acoustic and linguistic characteristics from raw audio and a set of metrics to evaluate the learned representations at acustic, linguistic and encoding levels.
Outcome: The proposed models evaluate the learned representations at acoustic and linguistic levels for both encoding and generation.
Exploring Cross-Lingual Voice Conversion Methods for Anonymizing Low-Resource Text-to-Speech (2026.eacl-short)

Copied to clipboard

Challenge: a growing number of speech synthesis systems clone a person's voice, a new study finds . a variety of voice conversion techniques can mask speaker identities in low-resource text-to-speech systems.
Approach: They compare voice conversion techniques to mask speaker identities in text-to-speech systems . they build and evaluate speaker-anonymized systems for two Canadian Indigenous languages .
Outcome: The proposed methods are compared with other approaches for using voice conversion to mask speaker identities in low-resource text-to-speech systems.
Revitalization of Indigenous Languages through Pre-processing and Neural Machine Translation: The case of Inuktitut (2020.coling-main)

Copied to clipboard

Challenge: Indigenous languages have been considered low-resource and/or endangered . authors propose a method to revitalize the language spoken in northern canada .
Approach: They propose to revitalize the Inuktitut language through pre-processing and neural machine translation . they propose to use this technique to perform morphological analysis and neural translation tasks .
Outcome: The proposed approach improves the Inuktitut language compared to the state-of-the-art . the proposed approach is based on preprocessing and neural machine translation .
Language Model Priors and Data Augmentation Strategies for Low-resource Machine Translation: A Case Study Using Finnish to Northern Sámi (2024.findings-acl)

Copied to clipboard

Challenge: a new study examines the use of monolingual data for improving low-resource machine translation.
Approach: They investigate ways of using monolingual data for improving low-resource machine translation.
Outcome: The proposed model can perform better on the target-side data without augmentation of parallel data.
Grammar-based Data Augmentation for Low-Resource Languages: The Case of Guarani-Spanish Neural Machine Translation (2024.naacl-long)

Copied to clipboard

Challenge: Low-resource languages suffer from a vicious circle: data is needed to build tools, but available text is scarce.
Approach: They propose to use a grammar-based system to generate Spanish text and syntactically transfer it to Guarani to boost its performance.
Outcome: The proposed system outperforms existing models by pretraining models with synthetic text.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations