ASR2K: Speech Recognition for Around 2000 Languages without Audio
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.
Code (1)
Tasks
Language ModelingLanguage ModellingSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
WorldSpeech: A Multilingual Speech Corpus from Around the World
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 RecognitionUnsupervised Speech Recognition
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 RecognitionZero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations
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+1Using Radio Archives for Low-Resource Speech Recognition: Towards an Intelligent Virtual Assistant for Illiterate Users
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+1Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper
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