activity
20192022
most citedUniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset

9 citations · 35 across the 7 of their papers we have counts for

collaborators

11 papers

cs.SD20222 cited

Deploying self-supervised learning in the wild for hybrid automatic speech recognition

Mostafa Karimi, Changliang Liu, Kenichi Kumatani +3

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly c…

cs.CL20224 cited

Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition

Kenichi Kumatani, Robert Gmyr, Felipe Cruz Salinas +5

The sparsely-gated Mixture of Experts (MoE) can magnify a network capacity with a little computational complexity. In this work, we investigate how multi-lingual Automatic Speech R…

cs.LG20218 cited

Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal

Tae Jin Park, Kenichi Kumatani, Dimitrios Dimitriadis

Federated Learning is a fast growing area of ML where the training datasets are extremely distributed, all while dynamically changing over time. Models need to be trained on client…

cs.CL20214 cited

Multilingual Speech Recognition using Knowledge Transfer across Learning Processes

Rimita Lahiri, Kenichi Kumatani, Eric Sun +1

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim…

eess.AS20219 cited

UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset

Chengyi Wang, Yu Wu, Shujie Liu +4

Recently, there has been a vast interest in self-supervised learning (SSL) where the model is pre-trained on large scale unlabeled data and then fine-tuned on a small labeled datas…

cs.LG2021

Dynamic Gradient Aggregation for Federated Domain Adaptation

Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr +2

In this paper, a new learning algorithm for Federated Learning (FL) is introduced. The proposed scheme is based on a weighted gradient aggregation using two-step optimization to of…