46 citations · 140 across the 12 of their papers we have counts for
14 papers
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…
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…
Sequence-level self-learning with multiple hypotheses
Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur +4
In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech…
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…
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…
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…
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…
UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data
Chengyi Wang, Yu Wu, Yao Qian +5
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 le…
Federated Transfer Learning with Dynamic Gradient Aggregation
Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr +2
In this paper, a Federated Learning (FL) simulation platform is introduced. The target scenario is Acoustic Model training based on this platform. To our knowledge, this is the fir…
Robust Multi-channel Speech Recognition using Frequency Aligned Network
Taejin Park, Kenichi Kumatani, Minhua Wu +1
Conventional speech enhancement technique such as beamforming has known benefits for far-field speech recognition. Our own work in frequency-domain multi-channel acoustic modeling…
Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning
Sanna Wager, Aparna Khare, Minhua Wu +2
In this work, we investigated the teacher-student training paradigm to train a fully learnable multi-channel acoustic model for far-field automatic speech recognition (ASR). Using…
Multi-Geometry Spatial Acoustic Modeling for Distant Speech Recognition
Kenichi Kumatani, Minhua Wu, Shiva Sundaram +2
The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrad…
Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition
Minhua Wu, Kenichi Kumatani, Shiva Sundaram +2
Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise o…
Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning
Ladislav Mošner, Minhua Wu, Anirudh Raju +5
For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean an…