Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

In this paper, several works are proposed to address practi-cal challenges for deploying
RNN Transducer (RNN-T) based speech recognition systems. These challenges are …

Non-intrusive intelligibility prediction is important for its application in realistic scenarios,
where a clean reference signal is difficult to access. The construction of many non-intrusive …

In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors
should be selected from the n-best list using a language model (LM). However, LMs are …

Protein ubiquitylation is an essential post-translational modification process that performs a
critical role in a wide range of biological functions, even a degenerative role in certain …

Voice assistant accessibility is generally overlooked as today's spoken dialogue systems are
trained on huge corpora to help them understand the 'average'user. This raises frustrating …

This article presents diana, a new, process-oriented model of human auditory word
recognition, which takes as its input the acoustic signal and can produce as its output word …

End-to-end models with auto-regressive decoders have shown impressive results for
automatic speech recognition (ASR). These models formulate the sequence-level probability …

This paper presents a class of new fast non-trainable entropy-based confidence estimation
methods for automatic speech recognition. We show how per-frame entropy values can be …

Although modern automatic speech recognition (ASR) systems can achieve high
performance, they may produce errors that weaken readers' experience and do harm to …