XLSR-53 a multilingual model of speech, builds a vector representation from audio, which allows for a range of computational treatments. The experiments reported here use this neural representation to estimate the degree of closeness between audio files, ultimately aiming to extract relevant linguistic properties. We use max-pooling to aggregate the neural representations from a "snippet-lect" (the speech in a 5-second audio snippet) to a "doculect" (the speech in a given resource), then to dialects and languages. We use data from corpora of 11 dialects belonging to 5 less-studied languages. Similarity measurements between the 11 corpora bring out greatest closeness between those that are known to be dialects of the same language. The findings suggest that (i) dialect/language can emerge among the various parameters characterizing audio files and (ii) estimates of overall phonetic/phonological closeness can be obtained for a little-resourced or fully unknown language. The findings help shed light on the type of information captured by neural representations of speech and how it can be extracted from these representations

Multilingual training is effective in improving low-resource ASR, which may partially be explained by phonetic representation sharing between languages. In end-to-end (E2E) ASR systems, graphemes are often used as basic modeling units, however graphemes may not be ideal for multilingual phonetic sharing. In this paper, we leverage International Phonetic Alphabet (IPA) based language-universal phonetic model to improve low-resource ASR performances, for the first time within the attention encoder-decoder architecture. We propose an adaptation method on the phonetic IPA model to further improve the proposed approach on extreme low-resource languages. Experiments carried out on the open-source MLS corpus and our internal databases show our approach outperforms baseline monolingual models and most state-of-the-art works. Our main approach and adaptation are effective on extremely low-resource languages, even within domain- and language-mismatched scenarios.

The performance of Automatic Speech Recognition systems (ASRs) has increased significantly with the development of modern neural network topologies and the use of massive amount of data to train the models [1]. Although the accuracy of recent models improved for high-resource languages, such as English, the development of ASR models in other languages is still a difficult task using the same technologies [2, 3]. In this scenario, Self-Supervised Learning (SSL), a method in which representations with semantic information are learned by using unlabelled data, emerged as an important advance, allowing the training of deeper models using less labelled data [4, 5]. In this line of work, this paper explores the use of the Wav2vec 2.0 [6], a framework for self-supervised learning of discrete representations from raw audio data. Wav2vec 2.0 (Figure 1) is inspired by previous works in unsupervised pre-training for speech recognition, that is, Wav2vec [7] and Vq-Wav2vec [4].