Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition
Confidence-based Filtering for Speech Dataset Curation with Generative Speech Enhancement Using Discrete Tokens
Exploring Pre-training Benefits on Phoneme Addition through Fine-tuning in Speech Synthesis
Non-Intrusive Binaural Speech Intelligibility Prediction Using Mamba for Hearing-Impaired Listeners
Eigenvoice Synthesis based on Model Editing for Speaker Generation
Speaker-agnostic Emotion Vector for Cross-speaker Emotion Intensity Control
Exploring the Capability of Mamba in Speech Applications
An Attribute Interpolation Method in Speech Synthesis by Model Merging
聴覚信号処理に基づく音声了解度の客観評価指標
Remixed2Remixed: Domain adaptation for speech enhancement by Noise2Noise learning with remixing
Structured State Space Decoder for Speech Recognition and Synthesis