paper-with-me

Papers

Towards interfacing large language models with ASR systems using confidence measures and prompting

2024-07-31 · Maryam Naderi, Enno Hermann, Alexandre Nanchen, Sevada Hovsepyan, Mathew Magimai. -Doss

As large language models (LLMs) grow in parameter size and capabilities, such as interaction through prompting, they open up new ways of interfacing with automatic speech recognition (ASR) systems beyond rescoring n-best lists. This work investigates post-hoc correction of ASR transcripts with LLMs. To avoid introducing errors into likely accurate transcripts, we propose a range of confidence-based filtering methods. Our results indicate that this can improve the performance of less competitive ASR systems.

📄 PDF Abstract BibTeX arXiv:2407.21414

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs

2024-07-31 · Elan Markowitz, Anil Ramakrishna, Jwala Dhamala, Ninareh Mehrabi 외

Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge. However, KGs and LLMs are often developed separately and must be integ…

Knowledge GraphsQuestion Answering

MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels

2025-02-20 · Xiaoou Liu, Zhen Lin, Longchao Da, Chacha Chen 외

Large Language Models (LLMs) require robust confidence estimation, particularly in critical domains like healthcare and law where unreliable outputs can lead to significant consequences. Despite much recent work in confi…

Multiple-choiceText Generation

Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?

2025-10-23 · Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras arxiv

Chain-of-thought (CoT) prompting is a common technique for improving the reasoning abilities of large language models (LLMs). However, extended reasoning is often unnecessary and substantially increases token usage. As s…

Improved Baselines for Data-efficient Perceptual Augmentation of LLMs

2024-03-20 · Théophane Vallaeys, Mustafa Shukor, Matthieu Cord, Jakob Verbeek

The abilities of large language models (LLMs) have recently progressed to unprecedented levels, paving the way to novel applications in a wide variety of areas. In computer vision, LLMs can be used to prime vision-langua…

Audio captioningImage CaptioningQuestion AnsweringVisual Question Answering

Practical Application of Domain Dependent Confidence Measurement for Spoken Language Understanding Systems

2018-06-01 · NAACL 2018 6 · Mahnoosh Mehrabani, David Thomson, Benjamin Stern

Spoken Language Understanding (SLU), which extracts semantic information from speech, is not flawless, specially in practical applications. The reliability of the output of an SLU system can be evaluated using a semantic…

Automatic Speech Recognition (ASR)Feature Engineeringintent-classificationIntent Classification+5