Related papers: Sequential Editing for Lifelong Training of Speech…

This paper investigates discrete and continuous speech representations in Large Language Model (LLM)-based Automatic Speech Recognition (ASR), organizing them by feature continuity and training approach into four categories: supervised and…

Automatic Speech Recognition (ASR) systems exhibit the best performance on speech that is similar to that on which it was trained. As such, underrepresented varieties including regional dialects, minority-speakers, and low-resource…

Large language models (LLMs) acquire information from pre-training corpora, but their stored knowledge can become inaccurate or outdated over time. Model editing addresses this challenge by modifying model parameters without retraining, and…

Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different…

We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate…

Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves. While existing knowledge editing approaches offer various solutions for knowledge updating, they often struggle with…

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on…

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…

In this work, we investigated the teacher-student training paradigm to train a fully learnable multi-channel acoustic model for far-field automatic speech recognition (ASR). Using a large offline teacher model trained on beamformed audio,…

Automatic Speech Recognition (ASR) has advanced with Speech Foundation Models (SFMs), yet performance degrades on dysarthric speech due to variability and limited data. This study as part of the submission to the Speech Accessibility…

This paper proposes a new approach to perform unsupervised fine-tuning and self-training using unlabeled speech data for recurrent neural network (RNN)-Transducer (RNN-T) end-to-end (E2E) automatic speech recognition (ASR) systems.…

Large Language Models (LLMs) have demonstrated substantial potential for error correction in Automatic Speech Recognition (ASR). However, most research focuses on utterances from short-duration speech recordings, which are the predominant…

Automatic speech recognition (ASR) has recently become an important challenge when using deep learning (DL). It requires large-scale training datasets and high computational and storage resources. Moreover, DL techniques and machine…

Research on automatic speech recognition (ASR) systems for electrolaryngeal speakers has been relatively unexplored due to small datasets. When training data is lacking in ASR, a large-scale pretraining and fine tuning framework is often…

As human-machine voice interfaces provide easy access to increasingly intelligent machines, many state-of-the-art automatic speech recognition (ASR) systems are proposed. However, commercial ASR systems usually have poor performance on…

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…

Self-supervised pre-training of a speech foundation model, followed by supervised fine-tuning, has shown impressive quality improvements on automatic speech recognition (ASR) tasks. Fine-tuning separate foundation models for many downstream…

Recent advancements in deep learning have significantly enhanced multilingual automatic speech recognition (ASR) due to the development of advanced model architectures and available large-scale multilingual datasets. Despite that,…

In recent years, end-to-end automatic speech recognition (ASR) systems have proven themselves remarkably accurate and performant, but these systems still have a significant error rate for entity names which appear infrequently in their…