Diversity is crucial to reducing the word error rate (WER) when fusing multiple automatic speech recognition (ASR) systems. We present an empirical analysis linking diversity and fusion performance. We transcribed speech from the first 2012 US Presidential debate using multiple ASR systems trained with the Kaldi toolkit. We used the N-best ROVER algorithm to perform hypothesis fusion and measur...

We found a crucial error in an earlier paper on cancer in elderly mice, Age distribution of cancer in mice: the incidence turnover at old age (Pompei et al., 2001). That paper's principal data set, the ED01 records, was scrambled when read and analyzed with a statistical software package. Having done our best to correct the error, and having subjected the data to a more exact extension of origi...

Sustainability is a wide concept that contains other concepts such as social responsibility and has been investigated with concepts such as competition sustainability, reporting sustainability, and social sustainability. The present study aims to investigate the role of social interest rate risk management (SIRRM) in the relationship between sustainability performance and investment ef...

The increasing incidence and high morbidity and mortality of hepatocellular carcinoma (HCC) have inspired the creation of the Liver Imaging Reporting and Data System (LI-RADS). LI-RADS aims to reduce variability in exam interpretation, improve communication, facilitate clinical therapeutic decisions, reduce omission of pertinent information, and facilitate the monitoring of outcomes. LI-RADS is...

The paper is focused on the Word Error Rate (WER) estimation in Analog to Digital Converters (ADCs) as specified in Annex A of the IEEE Std. 1241. The aim is to give a contribution for the next version of such standard. A new statistical approach for WER estimation, that can better integrate what it is stated in the standard, is proposed. In particular, Student’s t and chi-square distributions ...

Word error rate (WER), which is the most commonly used method of measuring automatic speech recognition (ASR) accuracy, penalizes all types of ASR errors equally. However, humans differentially weigh different types of ASR errors. They judge ASR errors that distort the meaning of the spoken message more harshly than those that do not. Aiming to align more closely with human perception of ASR ac...

This paper presents the results of a longitudinal study of ASR performance on ageing voices. Experiments were conducted on the audio recordings of the proceedings of the Supreme Court Of The United States (SCOTUS). Results show that the Automatic Speech Recognition (ASR) Word Error Rates (WERs) for elderly voices are significantly higher than those of adult voices. The word error rate increases...

We describe a novel method for tuning the decoding parameters of a speech-to-text system so as to minimize word error rate (WER) subject to an over-all time constraint. When applied to three sub-realtime systems for recognizing English conversational telephone speech, the method gave speed improvements of up to 21.1% while at the same time reducing WER by up to 6.7%.

This project compares the accuracy of two automatic speech recognition (ASR) systems–Bing Speech and YouTube’s automatic captions–across gender, race and four dialects of American English. The dialects included were chosen for their acoustic dissimilarity. Bing Speech had differences in word error rate (WER) between dialects and ethnicities, but they were not statistically reliable. YouTube’s a...