相关论文: Lip Reading for Low-resource Languages by Learning…

The advent of Large Language Models (LLMs) has significantly advanced the field of automated code generation. LLMs rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource…

In this study, we generate and maintain a database of 10 million virtual lipids through METiS's in-house de novo lipid generation algorithms and lipid virtual screening techniques. These virtual lipids serve as a corpus for pre-training,…

Lipreading, also known as visual speech recognition, aims to identify the speech content from videos by analyzing the visual deformations of lips and nearby areas. One of the significant obstacles for research in this field is the lack of…

Synthesizing realistic videos according to a given speech is still an open challenge. Previous works have been plagued by issues such as inaccurate lip shape generation and poor image quality. The key reason is that only motions and…

Many natural language processing (NLP) tasks make use of massively pre-trained language models, which are computationally expensive. However, access to high computational resources added to the issue of data scarcity of African languages…

It is challenging to train and deploy Transformer LMs for hybrid speech recognition 2nd pass re-ranking in low-resource languages due to (1) data scarcity in low-resource languages, (2) expensive computing costs for training and refreshing…

Although discrete speech tokens have exhibited strong potential for language model-based speech generation, their high bitrates and redundant timbre information restrict the development of such models. In this work, we propose LSCodec, a…

The phonological discrepancies between a speaker's native (L1) and the non-native language (L2) serves as a major factor for mispronunciation. This paper introduces a novel multilingual MDD architecture, L1-MultiMDD, enriched with L1-aware…

In this paper some of the different techniques used to localize the lips from the face are discussed and compared along with its processing steps. Lip localization is the basic step needed to read the lips for extracting visual information…

Large Language Models (LLMs) remain heavily centered on English, with limited performance in low-resource languages. Existing adaptation approaches, such as continual pre-training, demand significant computational resources. In the case of…

Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probing methods to a multilingual context, investigating the…

Lip reading involves interpreting a speaker's speech by analyzing sequences of lip movements. Currently, most models regard the left and right halves of the lips as a symmetrical whole, lacking a thorough investigation of their differences.…

Reasoning capabilities are crucial for Large Language Models (LLMs), yet a notable gap exists between English and non-English languages. To bridge this disparity, some works fine-tune LLMs to relearn reasoning capabilities in non-English…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

At least 360 million people worldwide have disabling hearing loss that frequently causes difficulties in day-to-day conversations. Hearing aids often fail to offer enough benefits and have low adoption rates. However, people with hearing…

As large language models (LLMs) gradually become integral tools for problem solving in daily life worldwide, understanding linguistic inequality is becoming increasingly important. Existing research has primarily focused on static analyses…

An increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to the availability of limited resources and…

Cross-modality generation is an emerging topic that aims to synthesize data in one modality based on information in a different modality. In this paper, we consider a task of such: given an arbitrary audio speech and one lip image of…

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English,…