Large language models (LLMs) demonstrate powerful capabilities, but they still face
challenges in practical applications, such as hallucinations, slow knowledge updates, and …

As Large Language Models (LLMs) become popular, there emerged an important trend of
using multimodality to augment the LLMs' generation ability, which enables LLMs to better …

ASR systems in real applications must be adapted on the fly to correctly recognize task-
specific contextual terms, such as contacts, application names and media entities. However …

Retrieval is a widely adopted approach for improving language models leveraging external
information. As the field moves towards multi-modal large language models, it is important to …

This paper explores speculative speech recognition (SSR), where we empower
conventional automatic speech recognition (ASR) with speculation capabilities, allowing the …

The success of retrieval-augmented language models in various natural language
processing (NLP) tasks has been constrained in automatic speech recognition (ASR) …

Despite the impressive performance of ASR models on mainstream benchmarks, their
performance on rare words is unsatisfactory. In enterprise settings, often a focused list of …

We recently developed a joint speech and language model (SLM [1]) which fuses a
pretrained foundational speech model and a large language model (LLM), while preserving …

Automatic speech recognition (ASR) systems can suffer from poor recall for various reasons,
such as noisy audio, lack of sufficient training data, etc. Previous work has shown that recall …

The kNN-CTC model has proven to be effective for monolingual automatic speech
recognition (ASR). However, its direct application to multilingual scenarios like code …