Related papers: Adaptive Multi-Corpora Language Model Training for…

Language models (LMs) have introduced a major paradigm shift in Natural Language Processing (NLP) modeling where large pre-trained LMs became integral to most of the NLP tasks. The LMs are intelligent enough to find useful and relevant…

End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…

Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the server using transcribed speech data. However, the server…

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

Over half of US adults with Alzheimer disease and related dementias remain undiagnosed, and speech-based screening offers a scalable detection approach. We compared large language model adaptation strategies for dementia detection using the…

Neural Machine Translation (NMT) is a new approach for automatic translation of text from one human language into another. The basic concept in NMT is to train a large Neural Network that maximizes the translation performance on a given…

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…

The use of low-rank adaptation (LoRA) with frozen pretrained language models (PLMs) has become increasing popular as a mainstream, resource-efficient modeling approach for memory-constrained hardware. In this study, we first explore how to…

To train neural machine translation models simultaneously on multiple tasks (languages), it is common to sample each task uniformly or in proportion to dataset sizes. As these methods offer little control over performance trade-offs, we…

Natural Language Processing (NLP) systems commonly leverage bag-of-words co-occurrence techniques to capture semantic and syntactic word relationships. The resulting word-level distributed representations often ignore morphological…

LLM-based automatic speech recognition (ASR), a well-established approach, connects speech foundation models to large language models (LLMs) through a speech-to-LLM projector, yielding promising results. A common design choice in these…

Deep neural networks (DNN) are quickly becoming the de facto standard modeling method for many natural language generation (NLG) tasks. In order for such models to truly be useful, they must be capable of correctly generating utterances for…

Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although the high-quality…

Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the…

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Data augmentation is a widely adopted technique utilized to improve the robustness of automatic speech recognition (ASR). Employing a fixed data augmentation strategy for all training data is a common practice. However, it is important to…

In general, the performance of automatic speech recognition (ASR) systems is significantly degraded due to the mismatch between training and test environments. Recently, a deep-learning-based image-to-image translation technique to…