Related papers: Large Language Models are Efficient Learners of No…

Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for various text based tasks, they are not robust for spoken…

Visual cues, like lip motion, have been shown to improve the performance of Automatic Speech Recognition (ASR) systems in noisy environments. We propose LipGER (Lip Motion aided Generative Error Correction), a novel framework for leveraging…

Retrieval-Augmented Generation (RAG) is a promising approach for mitigating the hallucination of large language models (LLMs). However, existing research lacks rigorous evaluation of the impact of retrieval-augmented generation on different…

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

Large language models (LLMs) have recently achieved impressive results in speech recognition across multiple modalities, including Auditory Speech Recognition (ASR), Visual Speech Recognition (VSR), and Audio-Visual Speech Recognition…

Enhancement reports (ERs) serve as a critical communication channel between users and developers, capturing valuable suggestions for software improvement. However, manually processing these reports is resource-intensive, leading to delays…

While Automatic Speech Recognition (ASR) is typically benchmarked by word error rate (WER), real-world applications ultimately hinge on semantic fidelity. This mismatch is particularly problematic for dysarthric speech, where articulatory…

Noisy training data can significantly degrade the performance of language-model-based classifiers, particularly in non-topical classification tasks. In this study we designed a methodological framework to assess the impact of denoising.…

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in end-to-end speaker diarization and recognition. However, their speaker discriminability remains limited due to the scarcity of large-scale conversational data…

While Large Language Models (LLMs) have demonstrated remarkable capabilities, their reliability is significantly compromised by hallucinations. Existing intrinsic self-correction methods attempt to address this, but often fail due to…

Large language model (LLM)-based automatic speech recognition (ASR) achieves strong performance but often incurs high computational costs. This work investigates how to obtain the best LLM-ASR performance efficiently. Through comprehensive…

Automatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the performance of downstream tasks like summarization. This issue is particularly pronounced…

Generative error correction (GER) with large language models (LLMs) has emerged as an effective post-processing approach to improve automatic speech recognition (ASR) performance. However, it often struggles with rare or domain-specific…

Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often introduce speaker errors, particularly during speaker…

Speech enhancement (SE) systems are typically evaluated using a variety of instrumental metrics. The use of automatic speech recognition (ASR) systems to evaluate SE performance is common in literature, usually in terms of word error rate…

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker…

This article concerns comparative studies on the Automatic Speech Recognition (ASR) model incorporated with the Large Language Model (LLM) used for medical interviews. The proposed solution is tested on polish language benchmarks and…

Semi-supervised learning in automatic speech recognition (ASR) typically relies on pseudo-labeling, which often suffers from confirmation bias and error accumulation due to noisy supervision. To address this limitation, we propose ReHear, a…

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

End-to-end automatic speech recognition (E2E ASR) systems have significantly improved speech recognition through training on extensive datasets. Despite these advancements, they still struggle to accurately recognize domain specific words,…