paper-with-me

Papers

Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining

2023-01-18 · Karol Nowakowski, Michal Ptaszynski, Kyoko Murasaki, Jagna Nieuważny

In recent years, neural models learned through self-supervised pretraining on large scale multilingual text or speech data have exhibited promising results for underresourced languages, especially when a relatively large amount of data from related language(s) is available. While the technology has a potential for facilitating tasks carried out in language documentation projects, such as speech transcription, pretraining a multilingual model from scratch for every new language would be highly impractical. We investigate the possibility for adapting an existing multilingual wav2vec 2.0 model for a new language, focusing on actual fieldwork data from a critically endangered tongue: Ainu. Specifically, we (i) examine the feasibility of leveraging data from similar languages also in fine-tuning; (ii) verify whether the model's performance can be improved by further pretraining on target language data. Our results show that continued pretraining is the most effective method to adapt a wav2vec 2.0 model for a new language and leads to considerable reduction in error rates. Furthermore, we find that if a model pretrained on a related speech variety or an unrelated language with similar phonological characteristics is available, multilingual fine-tuning using additional data from that language can have positive impact on speech recognition performance when there is very little labeled data in the target language.

📄 PDF Abstract BibTeX arXiv:2301.07295

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Linguistically Informed Tokenization Improves ASR for Underresourced Languages

2025-10-07 · Massimo Daul, Alessio Tosolini, Claire Bowern arxiv

Automatic speech recognition (ASR) is a crucial tool for linguists aiming to perform a variety of language documentation tasks. However, modern ASR systems use data-hungry transformer architectures, rendering them genera…

Speech Recognition

Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease

2026-03-23 · Abner Hernandez, Eunjung Yeo, Kwanghee Choi, Chin-Jou Li 외 arxiv

The limited availability of dysarthric speech data makes cross-lingual detection an important but challenging problem. A key difficulty is that speech representations often encode language-dependent structure that can co…

Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages

2026-02-01 · Yang Xiao, Eun-Jung Holden, Ting Dang arxiv

Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challenging due to data scarcity and efficiency co…

Computational EfficiencySpeech Recognition

Multilingual Simultaneous Speech Translation

2022-03-28 · Shashank Subramanya, Jan Niehues

Applications designed for simultaneous speech translation during events such as conferences or meetings need to balance quality and lag while displaying translated text to deliver a good user experience. One common appro…

Translation

Leveraging Parameter-Efficient Transfer Learning for Multi-Lingual Text-to-Speech Adaptation

2024-06-25 · Yingting Li, Ambuj Mehrish, Bryan Chew, Bo Cheng 외

Different languages have distinct phonetic systems and vary in their prosodic features making it challenging to develop a Text-to-Speech (TTS) model that can effectively synthesise speech in multilingual settings. Furthe…

Speech Synthesistext-to-speechText to SpeechTransfer Learning