mlsanityData to 14 Oct 2026

Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet

arXiv 2502.02703 ↗First posted 4 Feb 2025cs.CL cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We present lightweight flow matching multilingual text-to-speech (TTS) systems for Ojibwe, Mi'kmaq, and Maliseet, three Indigenous languages in North America. Our results show that training a multilingual TTS model on three typologically similar languages can improve the performance over monolingual models, especially when data are scarce. Attention-free architectures are highly competitive with self-attention architecture with higher memory efficiency. Our research not only advances technical development for the revitalization of low-resource languages but also highlights the cultural gap in human evaluation protocols, calling for a more community-centered approach to human evaluation.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 33 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

14 of 33 references.

References · 14

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  3. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  4. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  5. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  6. 2021FNet: Mixing Tokens with Fourier Transformscited by 347
  7. 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 153
  8. 2023Matcha-TTS: A fast TTS architecture with conditional flow matchingcited by 145
  9. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 60
  10. 2024Hydra: Bidirectional State Space Models Through Generalized Matrix Mixerscited by 44
  11. 2024Exploring the Capability of Mamba in Speech Applicationscited by 20
  12. 2024CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Modelscited by 13
2 more
  1. 2024FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filtercited by 6
  2. 2024MunTTS: A Text-to-Speech System for Mundaricited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025LingGym: How Far Are LLMs from Thinking Like Field Linguists?cited by 6

Similar, not cited

Close in wording, no citation either way

  1. 2025Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization
  2. 2026PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual Voice Cloning and Inference-Time Model Fusion
  3. 2026Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech
  4. 2026Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders
  5. 2025LatinX: Aligning a Multilingual TTS Model with Direct Preference Optimization
  6. 2025DiaMoE-TTS: A Unified IPA-Based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot Adaptation
  7. 2025ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation
  8. 2023Cross-lingual Knowledge Distillation via Flow-based Voice Conversion for Robust Polyglot Text-To-Speech