Related papers: Massively Multilingual Adversarial Speech Recognit…

End-to-end multilingual speech recognition involves using a single model training on a compositional speech corpus including many languages, resulting in a single neural network to handle transcribing different languages. Due to the fact…

The adaption of multilingual pre-trained LLMs into eloquent and helpful assistants is essential to facilitate their use across different language regions. In that spirit, we are the first to conduct an extensive study of the performance of…

If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset. To test this, we take multilingual in-context learning as a case study, where few-shot…

Multilingual Speech Recognition is one of the most costly AI problems, because each language (7,000+) and even different accents require their own acoustic models to obtain best recognition performance. Even though they all use the same…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

The "massively-multilingual" training of multilingual models is known to limit their utility in any one language, and they perform particularly poorly on low-resource languages. However, there is evidence that low-resource languages can…

In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many…

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

In a multilingual neural machine translation model that fully shares parameters across all languages, an artificial language token is usually used to guide translation into the desired target language. However, recent studies show that…

Multi-speaker TTS has to learn both linguistic embedding and text embedding to generate speech of desired linguistic content in desired voice. However, it is unclear which characteristic of speech results from speaker and which part from…

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality…

Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used…

End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling,…

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap…

Multilingual pre-trained models exhibit zero-shot cross-lingual transfer, where a model fine-tuned on a source language achieves surprisingly good performance on a target language. While studies have attempted to understand transfer, they…

Hate speech detection has become an important research topic within the past decade. More private corporations are needing to regulate user generated content on different platforms across the globe. In this paper, we introduce a study of…

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a…

We focus on the problem of search in the multilingual setting. Examining the problems of next-sentence prediction and inverse cloze, we show that at large scale, instance-based transfer learning is surprisingly effective in the multilingual…