Related papers: Optimized Tokenization for Transcribed Error Corre…

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

State-of-the-art techniques of artificial intelligence, in particular deep learning, are mostly data-driven. However, collecting and manually labeling a large scale dataset is both difficult and expensive. A promising alternative is to…

Expressive speech synthesis requires vibrant prosody and well-timed pauses. We propose an effective strategy to augment a small dataset to train an expressive end-to-end Text-to-Speech model. We merge audios of emotionally congruent text…

Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual…

Traditionally, NLP performance improvement has been focused on improving models and increasing the number of model parameters. NLP vocabulary construction has remained focused on maximizing the number of words represented through subword…

Recent breakthroughs in synthetic data generation approaches made it possible to produce highly photorealistic images which are hardly distinguishable from real ones. Furthermore, synthetic generation pipelines have the potential to…

Despite significant recent progress in the area of Brain-Computer Interface (BCI), there are numerous shortcomings associated with collecting Electroencephalography (EEG) signals in real-world environments. These include, but are not…

This study investigates the impact of morphological typology on tokenization and language modeling performance. We focus on languages with synthetic and analytical morphological structures and examine their productivity when tokenized using…

Transfer learning can significantly improve the sample efficiency of neural networks, by exploiting the relatedness between a data-scarce target task and a data-abundant source task. Despite years of successful applications, transfer…

Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we…

Synthetic data generation is an appealing tool for augmenting and enriching datasets, playing a crucial role in advancing artificial intelligence (AI) and machine learning (ML). Not only does synthetic data help build robust AI/ML datasets…

Existing Machine Translation (MT) research often suggests a single, fixed set of hyperparameters for word segmentation models, symmetric Byte Pair Encoding (BPE), which applies the same number of merge operations (NMO) to train tokenizers…

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping…

Progress in neural grammatical error correction (GEC) is hindered by the lack of annotated training data. Sufficient amounts of high-quality manually annotated data are not available, so recent research has relied on generating synthetic…

Training a high performance end-to-end speech (E2E) processing model requires an enormous amount of labeled speech data, especially in the era of data-centric artificial intelligence. However, labeled speech data are usually scarcer and…

The end-to-end speech synthesis model can directly take an utterance as reference audio, and generate speech from the text with prosody and speaker characteristics similar to the reference audio. However, an appropriate acoustic embedding…

Subword tokenization methods like Byte Pair Encoding (BPE) are widely used in large language models due to their balance of vocabulary compactness and representational power. However, they suffer from inefficiencies in representing rare…

This paper presents a comprehensive examination of the impact of tokenization strategies and vocabulary sizes on the performance of Arabic language models in downstream natural language processing tasks. Our investigation focused on the…

The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process…

Past vocabulary learning techniques identify relevant vocabulary before training, relying on statistical and entropy-based assumptions that largely neglect the role of model training. Empirically, we observe that trained translation models…