Hisashi Kawai

National Institute of Information and Communications Technology — Japan

Computer Science · Physical Sciences

19h-index1.9kcitations210works2.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(138), Speech and Audio Processing(100), Music and Audio Processing(64), Natural Language Processing Techniques(60), Speech and dialogue systems(42)

Publications210 total

Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR
2025· 1 cited
GST-BERT-TTS: Prosody Prediction Without Accentual Labels For Multi-Speaker TTS Using BERT With Global Style Tokens
2025
Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASR
arXiv (Cornell University)·2025Open Access
Mora-Level Prosody Prediction for Text-to-Speech Using Japanese BERT Without Accentual Labels
2025
Fast Neural Vocoder With Fundamental Frequency Control Using Finite Impulse Response Filters
IEEE Transactions on Audio Speech and Language Processing·2025Open Access
Phoneme-Level Duration Controllable Neural Text-to-Speech With Phoneme Embedding Skip Connection and Modified Gaussian Duration Modeling
IEEE Access·2025Open Access
Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR
arXiv (Cornell University)·2024Open Access
Investigating ASR Error Correction with Large Language Model and Multilingual 1-best Hypotheses
2024· 11 cited
FIRNet: Fundamental Frequency Controllable Fast Neural Vocoder With Trainable Finite Impulse Response Filter
2024· 3 cited
Convnext-TTS And Convnext-VC: Convnext-Based Fast End-To-End Sequence-To-Sequence Text-To-Speech And Voice Conversion
2024· 6 cited
Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-Based ASR
2024· 1 cited
Fast Neural Speech Waveform Generative Models With Fully-Connected Layer-Based Upsampling
IEEE Access·2024· 4 citedOpen Access
Generative linguistic representation for spoken language identification
arXiv (Cornell University)·2023Open Access
Generative Linguistic Representation for Spoken Language Identification
2023
WaveNeXt: ConvNeXt-Based Fast Neural Vocoder Without ISTFT layer
2023· 3 cited
Cross-Modal Alignment With Optimal Transport For CTC-Based ASR
2023· 5 cited
Neural domain alignment for spoken language recognition based on optimal transport
arXiv (Cornell University)·2023Open Access
Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-based ASR
arXiv (Cornell University)·2023Open Access
Cross-modal Alignment with Optimal Transport for CTC-based ASR
arXiv (Cornell University)·2023Open Access
Pronunciation-Aware Unique Character Encoding for RNN Transducer-Based Mandarin Speech Recognition
2022 IEEE Spoken Language Technology Workshop (SLT)·2023· 1 cited
page 1 of 11Next →

Frequent Co-authors

Tomoki Toda(15), Xugang Lu(14), Yoshinori Shiga(13), Takuma Okamoto(11), Komei Sugiura(10), Yu Tsao(8), Sheng Li(6), Aly Magassouba(6), Chiori Hori(6), Peng Shen(6), Ryoichi Takashima(5), Szu‐Wei Fu(4), Kentaro Tachibana(4), Minoru Tsuzaki(4), Naoyuki Kanda(3), Hideki Kashioka(3), Satoshi Nakamura(3), Keisuke Matsubara(3), Tetsuya Takiguchi(3), Teruhisa Misu(3)