b'Hsin-Min Wang'

research

∙ 09/18/2023

Utilizing Whisper to Enhance Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids

Automated assessment of speech intelligibility in hearing aid (HA) devic...

0 Ryandhimas E. Zezario, et al. ∙

research

∙ 08/18/2023

Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model

This study proposes a multi-task pseudo-label learning (MPL)-based non-i...

0 Ryandhimas E. Zezario, et al. ∙

research

∙ 06/11/2023

Mandarin Electrolaryngeal Speech Voice Conversion using Cross-domain Features

Patients who have had their entire larynx removed, including the vocal f...

0 Hsin-Hao Chen, et al. ∙

research

∙ 06/11/2023

Audio-Visual Mandarin Electrolaryngeal Speech Voice Conversion

Electrolarynx is a commonly used assistive device to help patients with ...

0 Yung-Lun Chien, et al. ∙

research

∙ 12/11/2022

BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithm

The performance of speech-processing models is heavily influenced by the...

0 Yu-Wen Chen, et al. ∙

research

∙ 10/27/2022

CasNet: Investigating Channel Robustness for Speech Separation

Recording channel mismatch between training and testing conditions has b...

0 Fan-Lin Wang, et al. ∙

research

∙ 10/27/2022

A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference

The lack of clean speech is a practical challenge to the development of ...

0 Li-Wei Chen, et al. ∙

research

∙ 09/21/2022

Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN

Singing voice synthesis (SVS) is the computer production of a human-like...

0 Yin-Ping Cho, et al. ∙

research

∙ 06/18/2022

NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling

For deep learning-based speech enhancement (SE) systems, the training-te...

0 Chi-Chang Lee, et al. ∙

research

∙ 04/09/2022

A Study of Using Cepstrogram for Countermeasure Against Replay Attacks

In this paper, we investigate the properties of the cepstrogram and demo...

0 Shih-kuang Lee, et al. ∙

research

∙ 04/07/2022

MTI-Net: A Multi-Target Speech Intelligibility Prediction Model

Recently, deep learning (DL)-based non-intrusive speech assessment model...

5 Ryandhimas E. Zezario, et al. ∙

research

∙ 04/07/2022

MBI-Net: A Non-Intrusive Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids

Improving the user's hearing ability to understand speech in noisy envir...

5 Ryandhimas E. Zezario, et al. ∙

research

∙ 04/01/2022

Filter-based Discriminative Autoencoders for Children Speech Recognition

Children speech recognition is indispensable but challenging due to the ...

0 Chiang-Lin Tai, et al. ∙

research

∙ 03/30/2022

Generation of Speaker Representations Using Heterogeneous Training Batch Assembly

In traditional speaker diarization systems, a well-trained speaker model...

0 Yu-Huai Peng, et al. ∙

research

∙ 03/30/2022

Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks

Because the performance of speech separation is excellent for speech in ...

0 Fan-Lin Wang, et al. ∙

research

∙ 03/30/2022

Multi-target Filter and Detector for Unknown-number Speaker Diarization

A strong representation of a target speaker can aid in extracting import...

0 Chin-yi Cheng, et al. ∙

research

∙ 03/28/2022

Subspace-based Representation and Learning for Phonotactic Spoken Language Recognition

Phonotactic constraints can be employed to distinguish languages by repr...

0 Hung-Shin Lee, et al. ∙

research

∙ 03/25/2022

Speech-enhanced and Noise-aware Networks for Robust Speech Recognition

Compensation for channel mismatch and noise interference is essential fo...

0 Hung-Shin Lee, et al. ∙

research

∙ 03/25/2022

Chain-based Discriminative Autoencoders for Speech Recognition

In our previous work, we proposed a discriminative autoencoder (DcAE) fo...

0 Hung-Shin Lee, et al. ∙

research

∙ 03/21/2022

The VoiceMOS Challenge 2022

We present the first edition of the VoiceMOS Challenge, a scientific eve...

0 Wen-Chin Huang, et al. ∙

research

∙ 02/14/2022

Partially Fake Audio Detection by Self-attention-based Fake Span Discovery

The past few years have witnessed the significant advances of speech syn...

0 Haibin Wu, et al. ∙

research

∙ 02/14/2022

EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement

Multimodal learning has been proven to be an effective method to improve...

0 Kuan-Chen Wang, et al. ∙

research

∙ 11/10/2021

HASA-net: A non-intrusive hearing-aid speech assessment network

Without the need of a clean reference, non-intrusive speech assessment m...

0 Hsin-Tien Chiang, et al. ∙

research

∙ 11/03/2021

Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features

In this study, we propose a cross-domain multi-objective speech assessme...

4 Ryandhimas E. Zezario, et al. ∙

research

∙ 10/19/2021

Speech Enhancement-assisted Stargan Voice Conversion in Noisy Environments

Numerous voice conversion (VC) techniques have been proposed for the con...

0 Yun-Ju Chan, et al. ∙

research

∙ 09/08/2021

Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion

Voice conversion (VC) is an effective approach to electrolaryngeal (EL) ...

0 Yi-Syuan Liou, et al. ∙

research

∙ 08/01/2021

SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours

The surprisingness of a song is an essential and seemingly subjective fa...

0 Yi-Wei Chen, et al. ∙

research

∙ 07/20/2021

SVSNet: An End-to-end Speaker Voice Similarity Assessment Model

Neural evaluation metrics derived for numerous speech generation tasks h...

1 Cheng-Hung Hu, et al. ∙

research

∙ 06/02/2021

A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion

We propose a new paradigm for maintaining speaker identity in dysarthric...

0 Wen-Chin Huang, et al. ∙

research

∙ 06/02/2021

Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving

With the recent advancements in deep learning, neural solvers have gaine...

0 Shih-hung Tsai, et al. ∙

research

∙ 05/01/2021

AlloST: Low-resource Speech Translation without Source Transcription

The end-to-end architecture has made promising progress in speech transl...

0 Yao-Fei Cheng, et al. ∙

research

∙ 04/07/2021

The AS-NU System for the M2VoC Challenge

This paper describes the AS-NU systems for two tracks in MultiSpeaker Mu...

0 Cheng-Hung Hu, et al. ∙

research

∙ 01/30/2021

Speech Recognition by Simply Fine-tuning BERT

We propose a simple method for automatic speech recognition (ASR) by fin...

0 Wen-Chin Huang, et al. ∙

research

∙ 12/17/2020

Speech Enhancement with Zero-Shot Model Selection

Recent research on speech enhancement (SE) has seen the emergence of dee...

0 Ryandhimas E. Zezario, et al. ∙

research

∙ 11/09/2020

STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model

The calculation of most objective speech intelligibility assessment metr...

0 Ryandhimas E. Zezario, et al. ∙

research

∙ 10/26/2020

Melody Harmonization Using Orderless NADE, Chord Balancing, and Blocked Gibbs Sampling

Coherence and interestingness are two criteria for evaluating the perfor...

0 Chung-En Sun, et al. ∙

research

∙ 10/06/2020

The Academia Sinica Systems of Voice Conversion for VCC2020

This paper describes the Academia Sinica systems for the two tasks of Vo...

0 Yu-Huai Peng, et al. ∙

research

∙ 08/30/2020

Improved Lite Audio-Visual Speech Enhancement

Numerous studies have investigated the effectiveness of audio-visual mul...

0 Shang-Yi Chuang, et al. ∙

research

∙ 05/24/2020

Lite Audio-Visual Speech Enhancement

Previous studies have confirmed the effectiveness of incorporating visua...

0 Shang-Yi Chuang, et al. ∙

research

∙ 05/24/2020

SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning

Numerous noise adaptation techniques have been proposed to address the m...

0 Chi-Chang Lee, et al. ∙

research

∙ 04/06/2020

WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement

Due to the simple design pipeline, end-to-end (E2E) neural models for sp...

0 Tsun-An Hsieh, et al. ∙

research

∙ 01/22/2020

Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion

An effective approach for voice conversion (VC) is to disentangle lingui...

0 Wen-Chin Huang, et al. ∙

research

∙ 01/06/2020

Speech Enhancement based on Denoising Autoencoder with Multi-branched Encoders

Deep learning-based models have greatly advanced the performance of spee...

0 Cheng Yu, et al. ∙

research

∙ 12/27/2019

MoEVC: A Mixture-of-experts Voice Conversion System with Sparse Gating Mechanism for Accelerating Online Computation

With the recent advancements of deep learning technologies, the performa...

0 Yu-Tao Chang, et al. ∙

research

∙ 11/19/2019

Distributed Microphone Speech Enhancement based on Deep Learning

Speech-related applications deliver inferior performance in complex nois...

0 Syu-Siang Wang, et al. ∙

research

∙ 11/05/2019

The ASVspoof 2019 database

Automatic speaker verification (ASV) is one of the most natural and conv...

0 Xin Wang, et al. ∙

research

∙ 09/26/2019

Improving the Intelligibility of Electric and Acoustic Stimulation Speech Using Fully Convolutional Networks Based Speech Enhancement

The combined electric and acoustic stimulation (EAS) has demonstrated be...

0 Natalie Yu-Hsien Wang, et al. ∙

research

∙ 09/26/2019

Multichannel Speech Enhancement by Raw Waveform-mapping using Fully Convolutional Networks

In recent years, waveform-mapping-based speech enhancement (SE) methods ...

0 Chang-Le Liu, et al. ∙

research

∙ 08/26/2019

Improving Automatic Jazz Melody Generation by Transfer Learning Techniques

In this paper, we tackle the problem of transfer learning for Jazz autom...

0 Hsiao-Tzu Hung, et al. ∙

research

∙ 05/02/2019

Investigation of F0 conditioning and Fully Convolutional Networks in Variational Autoencoder based Voice Conversion

In this work, we investigate the effectiveness of two techniques for imp...

0 Wen-Chin Huang, et al. ∙

Hsin-Min Wang

Featured Co-authors