Deep spoken keyword spotting: An overview

I López-Espejo, ZH Tan, JHL Hansen, J Jensen - IEEE Access, 2021 - ieeexplore.ieee.org
Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams
and has become a fast-growing technology thanks to the paradigm shift introduced by deep …

A comparative study on transformer vs rnn in speech applications

S Karita, N Chen, T Hayashi, T Hori… - 2019 IEEE automatic …, 2019 - ieeexplore.ieee.org
Sequence-to-sequence models have been widely used in end-to-end speech processing,
for example, automatic speech recognition (ASR), speech translation (ST), and text-to …

CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings

S Watanabe, M Mandel, J Barker, E Vincent… - ar** for utterance-wise and continuous speech separation
ZQ Wang, P Wang, DL Wang - IEEE/ACM transactions on …, 2021 - ieeexplore.ieee.org
We propose multi-microphone complex spectral map**, a simple way of applying deep
learning for time-varying non-linear beamforming, for speaker separation in reverberant …

Voices obscured in complex environmental settings (voices) corpus

C Richey, MA Barrios, Z Armstrong, C Bartels… - arxiv preprint arxiv …, 2018 - arxiv.org
This paper introduces the Voices Obscured In Complex Environmental Settings (VOICES)
corpus, a freely available dataset under Creative Commons BY 4.0. This dataset will …