相关论文: Multilingual training set selection for ASR in und…

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

We present our first efforts in building an automatic speech recognition system for Somali, an under-resourced language, using 1.57 hrs of annotated speech for acoustic model training. The system is part of an ongoing effort by the United…

Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly established a bottleneck (BN) layer by pre-training on a…

Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…

Bilingual and multilingual language models offer a promising path toward scaling NLP systems across diverse languages and users. However, their performance often varies wildly between languages as prior works show that adding more languages…

Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages,…

We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for…

Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks. In this work, we benchmark NMT between English and five African LRL pairs (Swahili, Amharic, Tigrigna, Oromo,…

In this paper, we propose a self-training approach for automatic speech recognition (ASR) for low-resource settings. While self-training approaches have been extensively developed and evaluated for high-resource languages such as English,…

This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to…

Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties…

Sequence-to-sequence attention-based models integrate an acoustic, pronunciation and language model into a single neural network, which make them very suitable for multilingual automatic speech recognition (ASR). In this paper, we are…

The performance of automatic speech recognition (ASR) systems has advanced substantially in recent years, particularly for languages for which a large amount of transcribed speech is available. Unfortunately, for low-resource languages,…

In this work, we present AfriHuBERT, an extension of mHuBERT-147, a compact self-supervised learning (SSL) model pretrained on 147 languages. While mHuBERT-147 covered 16 African languages, we expand this to 1,226 through continued…

Researchers working on low-resource languages face persistent challenges due to limited data availability and restricted access to computational resources. Although most large language models (LLMs) are predominantly trained in…

Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few…

In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech…

In this paper, we focus on the task of multilingual machine translation for African languages and describe our contribution in the 2021 WMT Shared Task: Large-Scale Multilingual Machine Translation. We introduce MMTAfrica, the first…

Multilingual Automated Speech Recognition (ASR) systems allow for the joint training of data-rich and data-scarce languages in a single model. This enables data and parameter sharing across languages, which is especially beneficial for the…

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…