Search Results for author: Kenichi Kumatani

Found 12 papers, 1 papers with code

Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal

no code implementations19 Oct 2021 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.

Federated Learning Incremental Learning

Multilingual Speech Recognition using Knowledge Transfer across Learning Processes

no code implementations15 Oct 2021 Rimita Lahiri, Kenichi Kumatani, Eric Sun, Yao Qian

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).

Automatic Speech Recognition Meta-Learning +3

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

no code implementations12 Jul 2021 Chengyi Wang, Yu Wu, Shujie Liu, Jinyu Li, Yao Qian, Kenichi Kumatani, Furu Wei

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 dataset.

Self-Supervised Learning speech-recognition +1

Dynamic Gradient Aggregation for Federated Domain Adaptation

no code implementations14 Jun 2021 Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez

The proposed scheme is based on a weighted gradient aggregation using two-step optimization to offer a flexible training pipeline.

Domain Adaptation Federated Learning +3

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

3 code implementations19 Jan 2021 Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang

In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised learning are conducted in a multi-task learning manner.

Multi-Task Learning Representation Learning +3

Robust Multi-channel Speech Recognition using Frequency Aligned Network

no code implementations6 Feb 2020 Taejin Park, Kenichi Kumatani, Minhua Wu, Shiva Sundaram

In this paper, we further develop this idea and use frequency aligned network for robust multi-channel automatic speech recognition (ASR).

Automatic Speech Recognition Speech Enhancement +1

Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning

no code implementations1 Feb 2020 Sanna Wager, Aparna Khare, Minhua Wu, Kenichi Kumatani, Shiva Sundaram

Using a large offline teacher model trained on beamformed audio, we trained a simpler multi-channel student acoustic model used in the speech recognition system.

Automatic Speech Recognition speech-recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.