← Authors

Hsin-Min Wang

39 papers · 2013–2024 · 6 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (14) 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (11) 🐝 Cross-Pollinator (5) 🌈 Renaissance Researcher (7) 🏠 Conference Loyalist (33) πŸ† Keyword Champion (3) 🀝 Dynamic Duo (30) 🌱 Topic Pioneer πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (159) πŸ’Ž Century Club (39) ⚑ Prolific Year (6) πŸš€ Conference Pioneer πŸ”₯ Unstoppable (9)

Conferences

INTERSPEECH (33) IJCNLP (2) ACL (1) COLING (1) EMNLP (1) ICLR (1)

Top co-authors

Yu Tsao (30) Hung-Shin Lee (9) Kuan-Yu Chen (7) Berlin Chen (5) Hsin-Te Hwang (5) YI-CHIAO WU (5) Yu-Huai Peng (4) Szu-Wei Fu (4) Tomoki Toda (4) Wen-Chin Huang (4)

Research topics

Optimization (1)

Keywords

voice conversion (8) speech enhancement (8) self-supervised learning (4) speech intelligibility (4) representation learning (3) variational autoencoder (3) locally linear embedding (3) deep learning (3) mean opinion score (3) noise adaptation (3) speaker verification (3) domain knowledge (2) speech separation (2) neural solver (2) feature extraction (2) speech synthesis (2) domain adaptation (2) transfer learning (2) speech recognition (2) multimodal learning (2)

Papers

SVSNet+: Enhancing Speaker Voice Similarity Assessment Models with Representations from Speech Foundation Models INTERSPEECH 2024
Learnable Layer Selection and Model Fusion for Speech Self-Supervised Learning Models INTERSPEECH 2024
Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata INTERSPEECH 2024
Audio-Visual Mandarin Electrolaryngeal Speech Voice Conversion INTERSPEECH 2023
D4AM: A General Denoising Framework for Downstream Acoustic Models ICLR 2023
A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech INTERSPEECH 2023
Mandarin Electrolaryngeal Speech Voice Conversion using Cross-domain Features INTERSPEECH 2023
MBI-Net: A Non-Intrusive Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids INTERSPEECH 2022
NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling INTERSPEECH 2022
MTI-Net: A Multi-Target Speech Intelligibility Prediction Model INTERSPEECH 2022
Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks INTERSPEECH 2022
The VoiceMOS Challenge 2022 INTERSPEECH 2022
Chain-based Discriminative Autoencoders for Speech Recognition INTERSPEECH 2022
Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving ACL 2021
Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving IJCNLP 2021
A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion INTERSPEECH 2021
AlloST: Low-Resource Speech Translation Without Source Transcription INTERSPEECH 2021
Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation INTERSPEECH 2021
Relational Data Selection for Data Augmentation of Speaker-Dependent Multi-Band MelGAN Vocoder INTERSPEECH 2021
Lite Audio-Visual Speech Enhancement INTERSPEECH 2020
SERIL: Noise Adaptive Speech Enhancement Using Regularization-Based Incremental Learning INTERSPEECH 2020
Noise Adaptive Speech Enhancement Using Domain Adversarial Training INTERSPEECH 2019
Specialized Speech Enhancement Model Selection Based on Learned Non-Intrusive Quality Assessment Metric INTERSPEECH 2019
Investigation of F0 Conditioning and Fully Convolutional Networks in Variational Autoencoder Based Voice Conversion INTERSPEECH 2019
MOSNet: Deep Learning-Based Objective Assessment for Voice Conversion INTERSPEECH 2019
Exploring the Encoder Layers of Discriminative Autoencoders for LVCSR INTERSPEECH 2019
Exemplar-Based Spectral Detail Compensation for Voice Conversion INTERSPEECH 2018
Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model Based on BLSTM INTERSPEECH 2018
Exploring the Use of Significant Words Language Modeling for Spoken Document Retrieval INTERSPEECH 2017
A Post-Filtering Approach Based on Locally Linear Embedding Difference Compensation for Speech Enhancement INTERSPEECH 2017
Wavelet Speech Enhancement Based on Robust Principal Component Analysis INTERSPEECH 2017
Voice Conversion from Unaligned Corpora Using Variational Autoencoding Wasserstein Generative Adversarial Networks INTERSPEECH 2017
Discriminative Autoencoders for Acoustic Modeling INTERSPEECH 2017
Learning to Distill: The Essence Vector Modeling Framework COLING 2016
Minimization of Regression and Ranking Losses with Shallow Neural Networks on Automatic Sincerity Evaluation INTERSPEECH 2016
Locally Linear Embedding for Exemplar-Based Spectral Conversion INTERSPEECH 2016
Exploring Word Mover’s Distance and Semantic-Aware Embedding Techniques for Extractive Broadcast News Summarization INTERSPEECH 2016
Leveraging Effective Query Modeling Techniques for Speech Recognition and Summarization EMNLP 2014
Semantic NaΓ―ve Bayes Classifier for Document Classification IJCNLP 2013