We propose a novel decentralized feature extraction approach in federated learning to
address privacy-preservation issues for speech recognition. It is built upon a quantum …

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 a neural language modeling system based on low-rank adaptation (LoRA) for
speech recognition output rescoring. Although pretrained language models (LMs) like BERT …

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

The rapid development of quantum computing has demonstrated many unique
characteristics of quantum advantages, such as richer feature representation and more …

Recent advances in large language models (LLMs) have stepped forward the development
of multilingual speech and machine translation by its reduced representation errors and …

This paper presents a parameter-efficient learning (PEL) to develop a low-resource accent
adaptation for text-to-speech (TTS). A resource-efficient adaptation from a frozen pre-trained …

We propose a novel neural model compression strategy combining data augmentation,
knowledge transfer, pruning, and quantization for device-robust acoustic scene classification …

End-to-End (E2E) automatic speech recognition (ASR) systems used in voice assistants
often have difficulties recognizing infrequent words personalized to the user, such as names …

Recent studies have demonstrated the efficacy of large language models (LLMs) in error
correction for automatic speech recognition (ASR). However, much of the research focuses …