Related papers: TiSpell: A Semi-Masked Methodology for Tibetan Spe…

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…

Models initialized from self-supervised pretraining may suffer from poor alignment with downstream tasks, reducing the extent to which subsequent fine-tuning can adapt pretrained features toward downstream objectives. To mitigate this, we…

Accurate spelling correction is a critical step in modern search interfaces, especially in an era of mobile devices and speech-to-text interfaces. For services that are deployed around the world, this poses a significant challenge for…

Recently, end-to-end (E2E) automatic speech recognition (ASR) models have made great strides and exhibit excellent performance in general speech recognition. However, there remain several challenging scenarios that E2E models are not…

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired…

Multilingual Pre-trained Language models (multiPLMs), trained on the Masked Language Modelling (MLM) objective are commonly being used for cross-lingual tasks such as bitext mining. However, the performance of these models is still…

We present the BME submission for the SIGMORPHON 2021 Task 0 Part 1, Generalization Across Typologically Diverse Languages shared task. We use an LSTM encoder-decoder model with three step training that is first trained on all languages,…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Steady-State Visual Evoked Potential (SSVEP) spellers are a promising communication tool for individuals with disabilities. This Brain-Computer Interface utilizes scalp potential data from (electroencephalography) EEG electrodes on a…

The growing prevalence of tampered images poses serious security threats, highlighting the urgent need for reliable detection methods. Multimodal large language models (MLLMs) demonstrate strong potential in analyzing tampered images and…

Segmentation remains an important preprocessing step both in languages where "words" or other important syntactic/semantic units (like morphemes) are not clearly delineated by white space, as well as when dealing with continuous speech…

Language models are aligned to the collective voice of many, resulting in generic outputs that do not align with specific users' styles. In this work, we present Trial-Error-Explain In-Context Learning (TICL), a tuning-free method that…

The effects of language mismatch impact speech anti-spoofing systems, while investigations and quantification of these effects remain limited. Existing anti-spoofing datasets are mainly in English, and the high cost of acquiring…

Large language models (LLMs) have been adopted to perform text-to-SQL tasks, utilizing their in-context learning (ICL) capability to translate natural language questions into structured query language (SQL). However, such a technique faces…

Data augmentation techniques are widely used in low-resource automatic morphological inflection to overcome data sparsity. However, the full implications of these techniques remain poorly understood. In this study, we aim to shed light on…

Recent results in end-to-end automatic speech recognition have demonstrated the efficacy of pseudo-labeling for semi-supervised models trained both with Connectionist Temporal Classification (CTC) and Sequence-to-Sequence (seq2seq) losses.…

Fine tuning self supervised pretrained models using pseudo labels can effectively improve speech recognition performance. But, low quality pseudo labels can misguide decision boundaries and degrade performance. We propose a simple yet…

The majority of Chinese characters are monophonic, while a special group of characters, called polyphonic characters, have multiple pronunciations. As a prerequisite of performing speech-related generative tasks, the correct pronunciation…

We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models.…

Labeling pixel-level masks for fine-grained semantic segmentation tasks, e.g. human parsing, remains a challenging task. The ambiguous boundary between different semantic parts and those categories with similar appearance usually are…