paper-with-me

홈 › Papers

ASR2K: Speech Recognition for Around 2000 Languages without Audio

2022-09-06 · Xinjian Li, Florian Metze, David R Mortensen, Alan W Black, Shinji Watanabe

Most recent speech recognition models rely on large supervised datasets, which are unavailable for many low-resource languages. In this work, we present a speech recognition pipeline that does not require any audio for the target language. The only assumption is that we have access to raw text datasets or a set of n-gram statistics. Our speech pipeline consists of three components: acoustic, pronunciation, and language models. Unlike the standard pipeline, our acoustic and pronunciation models use multilingual models without any supervision. The language model is built using n-gram statistics or the raw text dataset. We build speech recognition for 1909 languages by combining it with Crubadan: a large endangered languages n-gram database. Furthermore, we test our approach on 129 languages across two datasets: Common Voice and CMU Wilderness dataset. We achieve 50% CER and 74% WER on the Wilderness dataset with Crubadan statistics only and improve them to 45% CER and 69% WER when using 10000 raw text utterances.

📄 PDF Abstract BibTeX arXiv:2209.02842

Code (1)

xinjli/asr2k 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingSpeech Recognition

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

WorldSpeech: A Multilingual Speech Corpus from Around the World

2026-05-09 · Antonis Asonitis, Luca A. Lanzendörfer, Frédéric Berdoz, Roger Wattenhofer arxiv

Automatic speech recognition (ASR) performs well for high-resource languages with abundant paired audio-transcript data, but its accuracy degrades sharply for most languages due to limited publicly available aligned data…

Speech Recognition

Unsupervised Speech Recognition

2021-05-24 · NeurIPS 2021 12 · Alexei Baevski, Wei-Ning Hsu, Alexis Conneau, Michael Auli

Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper desc…

speech-recognitionSpeech RecognitionUnsupervised Speech Recognition

Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations

2025-03-08 · Jeong Hun Yeo, Minsu Kim, Chae Won Kim, Stavros Petridis 외

We explore a novel zero-shot Audio-Visual Speech Recognition (AVSR) framework, dubbed Zero-AVSR, which enables speech recognition in target languages without requiring any audio-visual speech data in those languages. Spe…

Audio-Visual Speech RecognitionMulti-Task Learningspeech-recognitionSpeech Recognition+1

Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users

2021-04-27 · Moussa Doumbouya, Lisa Einstein, Chris Piech

For many of the 700 million illiterate people around the world, speech recognition technology could provide a bridge to valuable information and services. Yet, those most in need of this technology are often the most und…

Language IdentificationRepresentation Learningspeech-recognitionSpeech Recognition+1

Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper

2023-09-15 · Jeong Hun Yeo, Minsu Kim, Shinji Watanabe, Yong Man Ro

This paper proposes a powerful Visual Speech Recognition (VSR) method for multiple languages, especially for low-resource languages that have a limited number of labeled data. Different from previous methods that tried t…

Language Identificationspeech-recognitionSpeech RecognitionVisual Speech Recognition