6 citations · 19 across the 17 of their papers we have counts for
4 papers · 1 filter
Efficient End-to-End Speech Recognition Using Performers in Conformers
Peidong Wang, DeLiang Wang
On-device end-to-end speech recognition poses a high requirement on model efficiency. Most prior works improve the efficiency by reducing model sizes. We propose to reduce the comp…
Speaker Separation Using Speaker Inventories and Estimated Speech
Peidong Wang, Zhuo Chen, DeLiang Wang +2
We propose speaker separation using speaker inventories and estimated speech (SSUSIES), a framework leveraging speaker profiles and estimated speech for speaker separation. SSUSIES…
Multitask Training with Text Data for End-to-End Speech Recognition
Peidong Wang, Tara N. Sainath, Ron J. Weiss
We propose a multitask training method for attention-based end-to-end speech recognition models. We regularize the decoder in a listen, attend, and spell model by multitask trainin…
Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation
Zhong-Qiu Wang, Peidong Wang, DeLiang Wang
We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditio…