Automated speech recognition (ASR) systems, which use sophisticated machine-learning
algorithms to convert spoken language to text, have become increasingly widespread …

Speech output technology is finding widespread application, including in scenarios where
intelligibility might be compromised–at least for some listeners–by adverse conditions …

This project evaluates the accuracy of YouTube's automatically-generated captions across
two genders and five dialect groups. Speakers' dialect and gender was controlled for by …

Automatic speech recognition (ASR) systems promise to deliver objective interpretation of
human speech. Practice and recent evidence suggests that the state-of-the-art (SotA) ASRs …

Teaching and Researching Listening provides a focused, state-of-the-art treatment of the
linguistic, psycholinguistic and pragmatic processes that are involved in oral language use …

Comprehensibility, a major concept in second language (L2) pronunciation research that
denotes listeners' perceptions of how easily they understand L2 speech, is central to …

Practice and recent evidence show that state-of-the-art (SotA) automatic speech recognition
(ASR) systems do not perform equally well for all speaker groups. Many factors can cause …

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 …

We present an approach to speech recognition that uses only a neural network to map
acoustic input to characters, a character-level language model, and a beam search …

This paper discusses how automatic speech recognition systems are and could be
designed, in order to best exploit the discriminative information encoded in human speech …