English
Related papers

Related papers: Style-agnostic evaluation of ASR using multiple re…

200 papers

Text data is commonly utilized as a primary input to enhance Speech Emotion Recognition (SER) performance and reliability. However, the reliance on human-transcribed text in most studies impedes the development of practical SER systems,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-25 Yuanchao Li , Peter Bell , Catherine Lai

Objective assessment of speech that reflects meaningful changes in communication is crucial for clinical decision making and reproducible research. While existing objective assessments, particularly reference-based approaches, can capture…

Sound · Computer Science 2026-02-17 Bence Mark Halpern , Thomas Tienkamp , Defne Abur , Tomoki Toda

Natural language processing of conversational speech requires the availability of high-quality transcripts. In this paper, we express our skepticism towards the recent reports of very low Word Error Rates (WERs) achieved by modern Automatic…

Automatic speech recognition (ASR) systems are predominantly evaluated using the Word Error Rate (WER). However, raw token-level metrics fail to capture semantic fidelity and routinely obscures the `diversity tax', the disproportionate…

Machine Learning · Computer Science 2026-03-06 Ting-Hui Cheng , Line H. Clemmensen , Sneha Das

The predominant metric for evaluating speech recognizers, the Word Error Rate (WER) has been extended in different ways to handle transcripts produced by long-form multi-talker speech recognizers. These systems process long transcripts…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-05 Thilo von Neumann , Christoph Boeddeker , Marc Delcroix , Reinhold Haeb-Umbach

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…

Computation and Language · Computer Science 2023-05-15 Emma O'Neill , Julie Carson-Berndsen

A common question being raised in automatic speech recognition (ASR) evaluations is how reliable is an observed word error rate (WER) improvement comparing two ASR systems, where statistical hypothesis testing and confidence interval (CI)…

Machine Learning · Statistics 2020-05-22 Zhe Liu , Fuchun Peng

Measuring the performance of automatic speech recognition (ASR) systems requires manually transcribed data in order to compute the word error rate (WER), which is often time-consuming and expensive. In this paper, we continue our effort in…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-11 Ahmed Ali , Steve Renals

Conventionally, Automatic Speech Recognition (ASR) systems are evaluated on their ability to correctly recognize each word contained in a speech signal. In this context, the word error rate (WER) metric is the reference for evaluating…

Computation and Language · Computer Science 2026-05-06 Thibault Bañeras Roux , Jane Wottawa , Mickael Rouvier , Teva Merlin , Richard Dufour

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…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-13 Danilo de Oliveira , Tal Peer , Timo Gerkmann

The most commonly used metrics for evaluating automatic speech transcriptions, namely Word Error Rate (WER) and Character Error Rate (CER), have been heavily criticized for their poor correlation to human perception and their inability to…

Computation and Language · Computer Science 2026-05-06 Thibault Bañeras-Roux , Mickael Rouvier , Jane Wottawa , Richard Dufour

Although modern automatic speech recognition (ASR) systems can achieve high performance, they may produce errors that weaken readers' experience and do harm to downstream tasks. To improve the accuracy and reliability of ASR hypotheses, we…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-11 Jing Du , Shiliang Pu , Qinbo Dong , Chao Jin , Xin Qi , Dian Gu , Ru Wu , Hongwei Zhou

Many studies have examined the shortcomings of word error rate (WER) as an evaluation metric for automatic speech recognition (ASR) systems. Since WER considers only literal word-level correctness, new evaluation metrics based on semantic…

Computation and Language · Computer Science 2023-12-04 Zitha Sasindran , Harsha Yelchuri , T. V. Prabhakar , Supreeth Rao

This paper presents a comprehensive evaluation of Urdu Automatic Speech Recognition (ASR) models. We analyze the performance of three ASR model families: Whisper, MMS, and Seamless-M4T using Word Error Rate (WER), along with a detailed…

Computation and Language · Computer Science 2025-06-09 Samee Arif , Sualeha Farid , Aamina Jamal Khan , Mustafa Abbas , Agha Ali Raza , Awais Athar

Speech-to-text errors made by automatic speech recognition (ASR) systems negatively impact downstream models. Error correction models as a post-processing text editing method have been recently developed for refining the ASR outputs.…

Computation and Language · Computer Science 2023-06-22 Ziji Zhang , Zhehui Wang , Rajesh Kamma , Sharanya Eswaran , Narayanan Sadagopan

Measuring automatic speech recognition (ASR) system quality is critical for creating user-satisfying voice-driven applications. Word Error Rate (WER) has been traditionally used to evaluate ASR system quality; however, it sometimes…

Computation and Language · Computer Science 2022-07-07 Suyoun Kim , Duc Le , Weiyi Zheng , Tarun Singh , Abhinav Arora , Xiaoyu Zhai , Christian Fuegen , Ozlem Kalinli , Michael L. Seltzer

Word Error Rate (WER) has been the predominant metric used to evaluate the performance of automatic speech recognition (ASR) systems. However, WER is sometimes not a good indicator for downstream Natural Language Understanding (NLU) tasks,…

Computation and Language · Computer Science 2021-04-07 Suyoun Kim , Abhinav Arora , Duc Le , Ching-Feng Yeh , Christian Fuegen , Ozlem Kalinli , Michael L. Seltzer

Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks.…

Computation and Language · Computer Science 2024-04-01 Yash Jain , David Chan , Pranav Dheram , Aparna Khare , Olabanji Shonibare , Venkatesh Ravichandran , Shalini Ghosh

We propose a new method for the calculation of error rates in Automatic Speech Recognition (ASR). This new metric is for languages that contain half characters and where the same character can be written in different forms. We implement our…

Computation and Language · Computer Science 2022-06-16 Priyanshi Shah , Harveen Singh Chadha , Anirudh Gupta , Ankur Dhuriya , Neeraj Chhimwal , Rishabh Gaur , Vivek Raghavan

Word Error Rate (WER) mischaracterizes ASR models' performance for African languages by combining phonological, tone, and other linguistic errors into a single lexical error. By contrast, Feature Error Rate (FER) has recently attracted…

Computation and Language · Computer Science 2026-02-05 Fei-Yueh Chen , Lateef Adeleke , C. M. Downey