Related papers: Internal Language Model Estimation based Adaptive …

Rule-based adaptation is a foundational approach to self-adaptation, characterized by its human readability and rapid response. However, building high-performance and robust adaptation rules is often a challenge because it essentially…

Building an automatic speech recognition (ASR) system from scratch requires a large amount of annotated speech data, which is difficult to collect in many languages. However, there are cases where the low-resource language shares a common…

Multilingual speech processing with self-supervised or supervised pre-trained Speech Foundation Models (SFM) has achieved strong performance on tasks like Language Identification (LID) and Automatic Speech Recognition (ASR). However, these…

Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary words - including named entities (NE) - and in adapting to new domains using only text data. This work…

Unsupervised domain adaptation (UDA) with pre-trained language models (PrLM) has achieved promising results since these pre-trained models embed generic knowledge learned from various domains. However, fine-tuning all the parameters of the…

As voice assistants become more ubiquitous, they are increasingly expected to support and perform well on a wide variety of use-cases across different domains. We present a domain-aware rescoring framework suitable for achieving…

As more and more information-rich data like video become available, utilizing multi-modal auxiliary information to enhance audio tasks has sparked widespread research interest. The recent surge in research on LLM-based audio models provides…

Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…

The mismatch between an external language model (LM) and the implicitly learned internal LM (ILM) of RNN-Transducer (RNN-T) can limit the performance of LM integration such as simple shallow fusion. A Bayesian interpretation suggests to…

Domain adaptation (DA) arises as an important problem in statistical machine learning when the source data used to train a model is different from the target data used to test the model. Recent advances in DA have mainly been…

Large Language Model (LLM) inference systems present significant challenges in statistical performance characterization due to dynamic workload variations, diverse hardware architectures, and complex interactions between model size, batch…

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…

Speech therapy is essential for rehabilitating speech disorders caused by neurological impairments such as stroke. However, traditional manual and computer-assisted systems are limited in real-time accessibility and articulatory motion…

The growing deployment of low-cost, distributed sensor networks in environmental and biomedical domains has enabled continuous, large-scale health monitoring. However, these systems often face challenges related to degraded data quality…

The domain adaptation of language models, including large language models (LLMs), has become increasingly important as the use of such models continues to expand. This study demonstrates the effectiveness of Composition to Augment Language…

Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target samples. Conventional AL methods do not consider the…

The internal language model (ILM) of the neural transducer has been widely studied. In most prior work, it is mainly used for estimating the ILM score and is subsequently subtracted during inference to facilitate improved integration with…

While retrieval-augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs, LLMs still suffer from hallucination, generating incorrect or irrelevant information. A common detection strategy…

Large language models (LLMs) have become proficient at solving a wide variety of tasks, including those involving multi-modal inputs. In particular, instantiating an LLM (such as LLaMA) with a speech encoder and training it on paired data…

The long-standing one-to-many problem of gold standard responses in open-domain dialogue systems presents challenges for automatic evaluation metrics. Though prior works have demonstrated some success by applying powerful Large Language…