← Authors

Takanori Ashihara

15 papers · 2019–2024 · 1 conference · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (27) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (5) 🧬 Topic Evolution 🀝 Dynamic Duo (14) πŸ—ƒοΈ Keyword Collector (66) ❓ The Questioner πŸ’Ž Century Club (15) πŸ”₯ Unstoppable (6)

Conferences

INTERSPEECH (15)

Top co-authors

Takafumi Moriya (14) Marc Delcroix (9) Tomohiro Tanaka (9) Hiroshi Sato (8) Ryo Masumura (7) Kohei Matsuura (7) Tsubasa Ochiai (5) Taichi Asami (4) Atsunori Ogawa (3) Mana Ihori (3)

Keywords

knowledge distillation (4) automatic speech recognition (4) self-supervised learning (4) speech representation (3) attention mechanism (2) speech recognition (2) speech summarization (2) model compression (2) end-to-end model (2) speaker embedding (1) linguistic knowledge (1) speech enhancement (1) zero-shot learning (1) feature representation (1) spoken language understanding (1) parameter-efficient fine-tuning (1) domain adaptation (1) language model (1) speech intelligibility (1) real-time processing (1)

Papers

Lightweight Zero-shot Text-to-Speech with Mixture of Adapters INTERSPEECH 2024
SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling INTERSPEECH 2024
Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding INTERSPEECH 2024
Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation INTERSPEECH 2024
Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss INTERSPEECH 2023
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data INTERSPEECH 2023
SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge? INTERSPEECH 2023
Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization INTERSPEECH 2023
Domain Adversarial Self-Supervised Speech Representation Learning for Improving Unknown Domain Downstream Tasks INTERSPEECH 2022
Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models INTERSPEECH 2022
Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture INTERSPEECH 2021
Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition INTERSPEECH 2021
Investigating the Impact of Spectral and Temporal Degradation on End-to-End Automatic Speech Recognition Performance INTERSPEECH 2021
Self-Distillation for Improving CTC-Transformer-Based ASR Systems INTERSPEECH 2020
Neural Whispered Speech Detection with Imbalanced Learning INTERSPEECH 2019