paper-with-me

홈 › Papers

Mai Ho'omāuna i ka 'Ai: Language Models Improve Automatic Speech Recognition in Hawaiian

2024-04-03 · Kaavya Chaparala, Guido Zarrella, Bruce Torres Fischer, Larry Kimura, Oiwi Parker Jones

In this paper we address the challenge of improving Automatic Speech Recognition (ASR) for a low-resource language, Hawaiian, by incorporating large amounts of independent text data into an ASR foundation model, Whisper. To do this, we train an external language model (LM) on ~1.5M words of Hawaiian text. We then use the LM to rescore Whisper and compute word error rates (WERs) on a manually curated test set of labeled Hawaiian data. As a baseline, we use Whisper without an external LM. Experimental results reveal a small but significant improvement in WER when ASR outputs are rescored with a Hawaiian LM. The results support leveraging all available data in the development of ASR systems for underrepresented languages.

📄 PDF Abstract BibTeX arXiv:2404.03073

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Recovering Missing Characters in Old Hawaiian Writing

2018-10-01 · EMNLP 2018 10 · Brendan Shillingford, Oiwi Parker Jones

In contrast to the older writing system of the 19th century, modern Hawaiian orthography employs characters for long vowels and glottal stops. These extra characters account for about one-third of the phonemes in Hawaiia…

Language ModelingLanguage ModellingReading ComprehensionTransliteration

Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text

2022-07-24 · Oiwi Parker Jones, Brendan Shillingford

In contrast to the older writing system of the 19th century, modern Hawaiian orthography employs characters for long vowels and glottal stops. These extra characters account for about one-third of the phonemes in Hawaiia…

Reading ComprehensionTransliteration

Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text

2018-10-15 · NIPS Workshop IRASL 2018 · Anonymous

In contrast to the older writing system of the 19th century, modern Hawaiian orthography employs characters for long vowels and glottal stops. These extra characters account for about one-third of the phonemes in Hawaiia…

Deep LearningReading ComprehensionTransliteration

An enhanced automatic speech recognition system for Arabic

2017-04-01 · WS 2017 4 · Mohamed Amine Menacer, Odile Mella, Dominique Fohr, Denis Jouvet 외

Automatic speech recognition for Arabic is a very challenging task. Despite all the classical techniques for Automatic Speech Recognition (ASR), which can be efficiently applied to Arabic speech recognition, it is essent…

Arabic Speech RecognitionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognition+1

Developing Automatic Speech Recognition for Scottish Gaelic

2022-06-01 · CLTW (LREC) 2022 6 · Lucy Evans, William Lamb, Mark Sinclair, Beatrice Alex

This paper discusses our efforts to develop a full automatic speech recognition (ASR) system for Scottish Gaelic, starting from a point of limited resource. Building ASR technology is important for documenting and revita…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition