2026· Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)· pp. 95-106· 0 citations· 41 references
TL;DR
It is demonstrated that increasing manually reviewed transcriptions consistently improves word and character error rates, while audio enhancement slightly reduces performance, highlighting the complex trade-offs in low-resource ASR development.
Abstract
This paper presents a study focused on advancing Automatic Speech Recognition (ASR) for the under-resourced language Dënë Su ˛ łıné through data-centric approaches. We explore multiple strategies to enhance the quality of training data—both audio recordings and tran-scriptions—to address the challenges posed by mixed-quality datasets. Our experiments investigate which data preparation techniques most effectively improve ASR performance in this context. Our findings show that reducing spelling variants of the same lexeme in the corpus significantly improves model generalization, resulting in a substantial increase in recognition accuracy. Additionally, we demonstrate that increasing manually reviewed transcriptions consistently improves word and character error rates, while audio enhancement slightly reduces performance, highlighting the complex trade-offs in low-resource ASR development.
Findings indicate that language-specific fine-tuning plays a more critical role than multilingual generalization in achieving accurate ASR for Indonesian and provide practical guidance for deploying ASR systems in low-resource language scenarios.
J. Hebert, Amalia Zahra· Bulletin of Electrical Engin...· 0 citations
This work addresses the challenge of building robust foundation models for underrepresented Central Asian languages by presenting GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective, and introduces a cluster-level data balancing strategy during pre-training and a dom...
Andrei Kuzmenko, A. Maximenko, Aleksandr Kutsakov et al.· arXiv.org· 0 citations
The results show that encoder-based metrics remain highly competitive, while generative LLMs perform strongly in hypothesis comparison and improve the interpretability of ASR evaluation.
Thibault Bañeras-Roux, Shashi Kumar, Driss Khalil et al.· 0 citations
Text-to-speech systems are improving fast, but measuring how natural they sound still requires expensive human listening tests. Existing automatic methods struggle to generalise well across different datasets. We present QMOS, a MOS prediction framework that extracts hierarchical speech quality features from a frozen Q...
Ravi Sastry Kolluru, S. Devarakonda, S. Radhe Shyam Salopanthula et al.· International Conference on...· 0 citations
A cascaded diarization-then-recognition system that combines DiariZen-Large-s80 (WavLM-Large) segmentation, CAM++ embedding-based two-speaker clustering, and a LoRA-adapted omniASR LLM 7B v2 recognizer, with no oracle segmentation or speaker labels at test time is described.
Easper is presented, an open-source, no-code workflow enabling linguists to iteratively fine-tune ASR models via cloud resources directly from ELAN annotations, demonstrating that prioritising lexically rich narratives and increasing acoustic-phonetic repetition, even in noisy environments, leads to faster improvements...
Aso Mahmudi, Ting Dang, Ekaterina Vylomova et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
