1.9k citations · 2.2k across the 28 of their papers we have counts for
5 papers · 1 filter
C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling
Yutai Hou, Sanyuan Chen, Wanxiang Che +2
Slot filling, a fundamental module of spoken language understanding, often suffers from insufficient quantity and diversity of training data. To remedy this, we propose a novel Clu…
Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer
Sanyuan Chen, Yu Wu, Zhuo Chen +3
With its strong modeling capacity that comes from a multi-head and multi-layer structure, Transformer is a very powerful model for learning a sequential representation and has been…
Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020
Xiong Xiao, Naoyuki Kanda, Zhuo Chen +10
This paper describes the Microsoft speaker diarization system for monaural multi-talker recordings in the wild, evaluated at the diarization track of the VoxCeleb Speaker Recogniti…
Continuous Speech Separation with Conformer
Sanyuan Chen, Yu Wu, Zhuo Chen +6
Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a…
Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting
Sanyuan Chen, Yutai Hou, Yiming Cui +3
Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts t…