research
∙
06/04/2023
End-to-End Joint Target and Non-Target Speakers ASR
This paper proposes a novel automatic speech recognition (ASR) system th...
share
research
∙
05/24/2023
Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss
Self-supervised learning (SSL) is the latest breakthrough in speech proc...
research
∙
10/28/2022
On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis
This paper investigates the effectiveness and implementation of modality...
research
∙
09/09/2022
Streaming Target-Speaker ASR with Neural Transducer
Although recent advances in deep learning technology have boosted automa...
research
∙
06/16/2022
Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations
Target speech extraction is a technique to extract the target speaker's ...
research
∙
04/11/2022
Listen only to me! How well can target speech extraction handle false alarms?
Target speech extraction (TSE) extracts the speech of a target speaker i...
research
∙
01/18/2022
How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR
It is challenging to improve automatic speech recognition (ASR) performa...
research
∙
01/11/2022
Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition
The combination of a deep neural network (DNN) -based speech enhancement...
research
∙
06/02/2021
Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition
Although recent advances in deep learning technology improved automatic ...
research
∙
02/02/2021