Related papers: Cross-lingual Back-Parsing: Utterance Synthesis fr…

Based on large-scale pre-trained multilingual representations, recent cross-lingual transfer methods have achieved impressive transfer performances. However, the performance of target languages still lags far behind the source language. In…

Prompt-based tuning has been proven effective for pretrained language models (PLMs). While most of the existing work focuses on the monolingual prompts, we study the multilingual prompts for multilingual PLMs, especially in the zero-shot…

Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality…

Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to…

Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of…

Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an…

Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in leveraging nonverbal information for discerning complex…

Cross-lingual Machine Reading Comprehension (CLMRC) remains a challenging problem due to the lack of large-scale annotated datasets in low-source languages, such as Arabic, Hindi, and Vietnamese. Many previous approaches use translation…

Effectively using Natural Language Processing (NLP) tools in under-resourced languages requires a thorough understanding of the language itself, familiarity with the latest models and training methodologies, and technical expertise to…

We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of…

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data…

Although large language models(LLMs) show amazing capabilities, among various exciting applications discovered for LLMs fall short in other low-resource languages. Besides, most existing methods depend on large-scale dialogue corpora and…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Cross-lingual synthesis can be defined as the task of letting a speaker generate fluent synthetic speech in another language. This is a challenging task, and resulting speech can suffer from reduced naturalness, accented speech, and/or loss…

End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which…

The longstanding goal of multi-lingual learning has been to develop a universal cross-lingual model that can withstand the changes in multi-lingual data distributions. There has been a large amount of work to adapt such multi-lingual models…

Linguistic knowledge plays a crucial role in spoken language comprehension. It provides essential semantic and syntactic context for speech perception in noisy environments. However, most speech enhancement (SE) methods predominantly rely…

Cross-lingual adaptation, a special case of domain adaptation, refers to the transfer of classification knowledge between two languages. In this article we describe an extension of Structural Correspondence Learning (SCL), a recently…