Recent advancements in deep learning (DL) have posed a significant challenge for
automatic speech recognition (ASR). ASR relies on extensive training datasets, including …

Advancements in deep neural networks have allowed automatic speech recognition (ASR)
systems to attain human parity on several publicly available clean speech datasets …

We introduce a new cross-modal fusion technique designed for generative error correction
in automatic speech recognition (ASR). Our methodology leverages both acoustic …

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which
leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) …

We present a novel Speech Augmented Language Model (SALM) with multitask and in-
context learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a …

Given recent advances in generative AI technology, a key question is how large language
models (LLMs) can enhance acoustic modeling tasks using text decoding results from a …

Recent advances in large language models (LLMs) have promoted generative error
correction (GER) for automatic speech recognition (ASR), which leverages the rich linguistic …

Large language models (LLMs) have demonstrated remarkable advancements in language
understanding and generation. Building on the success of text-based LLMs, recent research …

Large Language Models (LLMs) have proven successful across a spectrum of speech-
related tasks, such as speech recognition, text-to-speech, and spoken language …

This paper presents an efficient decoding approach for end-to-end automatic speech
recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the …