activity
20172022
most citedOn Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression

303 citations · 631 across the 26 of their papers we have counts for

collaborators
Showing 2019Show all

8 papers · 1 filter

eess.AS2019

Attention-based gated scaling adaptative acoustic model for ctc-based speech recognition

Fenglin Ding, Wu Guo, Lirong Dai +1

In this paper, we propose a novel adaptive technique that uses an attention-based gated scaling (AGS) scheme to improve deep feature learning for connectionist temporal classificat…

eess.AS2019

Speaker detection in the wild: Lessons learned from JSALT 2019

Paola Garcia, Jesus Villalba, Herve Bredin +21

This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios. The main focus was to tack…

cs.CV2019

Joint Architecture and Knowledge Distillation in CNN for Chinese Text Recognition

Zi-Rui Wang, Jun Du

The technique of distillation helps transform cumbersome neural network into compact network so that the model can be deployed on alternative hardware devices. The main advantages…

cs.CV2019

Adaptive Period Embedding for Representing Oriented Objects in Aerial Images

Yixing Zhu, Xueqing Wu, Jun Du

We propose a novel method for representing oriented objects in aerial images named Adaptive Period Embedding (APE). While traditional object detection methods represent object with…

eess.AS2019

The Second DIHARD Diarization Challenge: Dataset, task, and baselines

Neville Ryant, Kenneth Church, Christopher Cieri +4

This paper introduces the second DIHARD challenge, the second in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variation i…

eess.AS2019

Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification

Lanhua You, Wu Guo, Lirong Dai +1

In this paper, gating mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, a gated convolution neural netwo…