Takafumi Moriya

Orcid: 0000-0003-1942-7250

According to our database1, Takafumi Moriya authored at least 49 papers between 2015 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis.
CoRR, 2024

Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters.
CoRR, 2024

2023
SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?
CoRR, 2023

Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization.
CoRR, 2023

End-to-End Joint Target and Non-Target Speakers ASR.
CoRR, 2023

Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss.
CoRR, 2023

Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection.
IEEE Access, 2023

Leveraging Language Embeddings for Cross-Lingual Self-Supervised Speech Representation Learning.
Proceedings of the IEEE International Conference on Acoustics, 2023

Iterative Shallow Fusion of Backward Language Model for End-To-End Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2023

Improving Scheduled Sampling for Neural Transducer-Based ASR.
Proceedings of the IEEE International Conference on Acoustics, 2023

Leveraging Large Text Corpora For End-To-End Speech Summarization.
Proceedings of the IEEE International Conference on Acoustics, 2023

Zero-Shot Text-to-Speech Synthesis Conditioned Using Self-Supervised Speech Representation Model.
Proceedings of the IEEE International Conference on Acoustics, 2023

Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models.
Proceedings of the IEEE International Conference on Acoustics, 2023

2022
On the Use of Modality-Specific Large-Scale Pre-Trained Encoders for Multimodal Sentiment Analysis.
Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Domain Adversarial Self-Supervised Speech Representation Learning for Improving Unknown Domain Downstream Tasks.
Proceedings of the Interspeech 2022, 2022

Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations.
Proceedings of the Interspeech 2022, 2022

Streaming Target-Speaker ASR with Neural Transducer.
Proceedings of the Interspeech 2022, 2022

End-to-End Joint Modeling of Conversation History-Dependent and Independent ASR Systems with Multi-History Training.
Proceedings of the Interspeech 2022, 2022

Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models.
Proceedings of the Interspeech 2022, 2022

Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2022

Hybrid RNN-T/Attention-Based Streaming ASR with Triggered Chunkwise Attention and Dual Internal Language Model Integration.
Proceedings of the IEEE International Conference on Acoustics, 2022

Customer Satisfaction Estimation Using Unsupervised Representation Learning with Multi-Format Prediction Loss.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Investigating the Impact of Spectral and Temporal Degradation on End-to-End Automatic Speech Recognition Performance.
Proceedings of the Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August, 2021

Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2021

Speech Emotion Recognition Based on Listener Adaptive Models.
Proceedings of the IEEE International Conference on Acoustics, 2021

2020
Self-Distillation for Improving CTC-Transformer-Based ASR Systems.
Proceedings of the Interspeech 2020, 2020

Distilling Attention Weights for CTC-Based ASR Systems.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Sequence-Level Consistency Training for Semi-Supervised End-to-End Automatic Speech Recognition.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition.
IEEE ACM Trans. Audio Speech Lang. Process., 2019

Does Speaking Training Application with Speech Recognition Motivate Junior High School Students in Actual Classroom? - A Case Study.
Proceedings of the 8th ISCA International Workshop on Speech and Language Technology in Education, 2019

A Joint End-to-End and DNN-HMM Hybrid Automatic Speech Recognition System with Transferring Sharable Knowledge.
Proceedings of the Interspeech 2019, 2019

Joint Maximization Decoder with Neural Converters for Fully Neural Network-Based Japanese Speech Recognition.
Proceedings of the Interspeech 2019, 2019

End-to-End Automatic Speech Recognition with a Reconstruction Criterion Using Speech-to-Text and Text-to-Speech Encoder-Decoders.
Proceedings of the Interspeech 2019, 2019

Neural Whispered Speech Detection with Imbalanced Learning.
Proceedings of the Interspeech 2019, 2019

Large Context End-to-end Automatic Speech Recognition via Extension of Hierarchical Recurrent Encoder-decoder Models.
Proceedings of the IEEE International Conference on Acoustics, 2019

Disfluency Detection Based on Speech-Aware Token-by-Token Sequence Labeling with BLSTM-CRFs and Attention Mechanisms.
Proceedings of the 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2019

Revisiting Dynamic Adjustment of Language Model Scaling Factor for Automatic Speech Recognition.
Proceedings of the 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2019

2018
Efficient Building Strategy with Knowledge Distillation for Small-Footprint Acoustic Models.
Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Automatic DNN Node Pruning Using Mixture Distribution-based Group Regularization.
Proceedings of the Interspeech 2018, 2018

Encoder Transfer for Attention-based Acoustic-to-word Speech Recognition.
Proceedings of the Interspeech 2018, 2018

Multi-task Learning with Augmentation Strategy for Acoustic-to-word Attention-based Encoder-decoder Speech Recognition.
Proceedings of the Interspeech 2018, 2018

Neural Speech-to-Text Language Models for Rescoring Hypotheses of DNN-HMM Hybrid Automatic Speech Recognition Systems.
Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

Progressive Neural Network-based Knowledge Transfer in Acoustic Models.
Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

Relevant Phonetic-aware Neural Acoustic Models using Native English and Japanese Speech for Japanese-English Automatic Speech Recognition.
Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, 2018

2016
Automated structure discovery and parameter tuning of neural network language model based on evolution strategy.
Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

2015
Automation of system building for state-of-the-art large vocabulary speech recognition using evolution strategy.
Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding, 2015


  Loading...