D
Dong Yu
Researcher at Tencent
Publications - 389
Citations - 45733
Dong Yu is an academic researcher from Tencent. The author has contributed to research in topics: Artificial neural network & Word error rate. The author has an hindex of 72, co-authored 339 publications receiving 39098 citations. Previous affiliations of Dong Yu include Peking University & Microsoft.
Papers
More filters
Proceedings Article
SafeConv: Explaining and Correcting Conversational Unsafe Behavior
TL;DR: SafeConv as mentioned in this paper provides unsafe spans in an utterance, information able to indicate which words contribute to the detected unsafe behavior, and SafeConv provides safe alternative responses to continue the conversation when unsafe behavior detected, guiding the conversation to a gentle trajectory.
Proceedings ArticleDOI
Deep Neural Mel-Subband Beamformer for In-car Speech Separation
TL;DR: In this paper , a DL-based mel-subband spatio-temporal beamformer was proposed to perform speech separation in a car environment with reduced computation cost and inference time.
Posted Content
Overlapped speech recognition from a jointly learned multi-channel neural speech extraction and representation.
TL;DR: An end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition that achieves 28% word error rate reduction over a separately optimized system on AISHELL-1 and shows consistent robustness to signal to interference ratio (SIR) and angle difference between overlapping speakers.
Posted Content
Learning discriminative features in sequence training without requiring framewise labelled data
TL;DR: This work proposes a novel method which simultaneously models both the sequence discriminative training and the feature discrim inative learning within a single network architecture, so that it can learn discriminatives deep features in sequence training that obviates the need for presegmented training data.
Journal ArticleDOI
Hybrid AHS: A Hybrid of Kalman Filter and Deep Learning for Acoustic Howling Suppression
TL;DR: In this paper , a hybrid method that combines a Kalman filter with a self-attentive recurrent neural network (SARNN) was proposed to leverage their respective advantages for robust acoustic howling suppression.