paper-with-me

Papers

Open Challenge for Correcting Errors of Speech Recognition Systems

2020-01-09 · Marek Kubis, Zygmunt Vetulani, Mikołaj Wypych, Tomasz Ziętkiewicz

The paper announces the new long-term challenge for improving the performance of automatic speech recognition systems. The goal of the challenge is to investigate methods of correcting the recognition results on the basis of previously made errors by the speech processing system. The dataset prepared for the task is described and evaluation criteria are presented.

📄 PDF Abstract BibTeX arXiv:2001.03041

Code (0)

등록된 구현이 없습니다.

Tasks

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

Similar Papers 제목 키워드 기반

Large Language Models based ASR Error Correction for Child Conversations

2025-05-22 · Anfeng Xu, Tiantian Feng, So Hyun Kim, Somer Bishop 외

Automatic Speech Recognition (ASR) has recently shown remarkable progress, but accurately transcribing children's speech remains a significant challenge. Recent developments in Large Language Models (LLMs) have shown pro…

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

Resilience of Large Language Models for Noisy Instructions

2024-04-15 · Bin Wang, Chengwei Wei, Zhengyuan Liu, Geyu Lin 외

As the rapidly advancing domain of natural language processing (NLP), large language models (LLMs) have emerged as powerful tools for interpreting human commands and generating text across various tasks. Nonetheless, the…

Automatic Speech RecognitionOptical Character RecognitionOptical Character Recognition (OCR)speech-recognition+1

Tag and correct: high precision post-editing approach to correction of speech recognition errors

2024-06-11 · Tomasz Ziętkiewicz

This paper presents a new approach to the problem of correcting speech recognition errors by means of post-editing. It consists of using a neural sequence tagger that learns how to correct an ASR (Automatic Speech Recogn…

Automatic Speech Recognitionspeech-recognitionSpeech RecognitionTAG

Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition

2019-08-21 · Piotr Żelasko, Jan Mizgajski, Mikołaj Morzy, Adrian Szymczak 외

In this paper, we present a method for correcting automatic speech recognition (ASR) errors using a finite state transducer (FST) intent recognition framework. Intent recognition is a powerful technique for dialog flow m…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Intent RecognitionManagement+2

Retrieval Augmented Correction of Named Entity Speech Recognition Errors

2024-09-09 · Ernest Pusateri, Anmol Walia, Anirudh Kashi, Bortik Bandyopadhyay 외

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 infreq…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)RAGRetrieval+3