Picture for Hsin-Min Wang

Hsin-Min Wang

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

Add code
Jul 20, 2021
Figure 1 for SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Figure 2 for SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Figure 3 for SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Figure 4 for SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Viaarxiv icon

Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation

Add code
Jun 14, 2021
Figure 1 for Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation
Figure 2 for Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation
Figure 3 for Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation
Figure 4 for Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation
Viaarxiv icon

Relational Data Selection for Data Augmentation of Speaker-dependent Multi-band MelGAN Vocoder

Add code
Jun 10, 2021
Figure 1 for Relational Data Selection for Data Augmentation of Speaker-dependent Multi-band MelGAN Vocoder
Figure 2 for Relational Data Selection for Data Augmentation of Speaker-dependent Multi-band MelGAN Vocoder
Figure 3 for Relational Data Selection for Data Augmentation of Speaker-dependent Multi-band MelGAN Vocoder
Viaarxiv icon

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

Add code
Jun 02, 2021
Figure 1 for A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
Figure 2 for A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
Figure 3 for A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
Figure 4 for A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion
Viaarxiv icon

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

Add code
Jun 02, 2021
Figure 1 for Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
Figure 2 for Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
Figure 3 for Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
Figure 4 for Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving
Viaarxiv icon

AlloST: Low-resource Speech Translation without Source Transcription

Add code
May 01, 2021
Figure 1 for AlloST: Low-resource Speech Translation without Source Transcription
Figure 2 for AlloST: Low-resource Speech Translation without Source Transcription
Figure 3 for AlloST: Low-resource Speech Translation without Source Transcription
Figure 4 for AlloST: Low-resource Speech Translation without Source Transcription
Viaarxiv icon

The AS-NU System for the M2VoC Challenge

Add code
Apr 07, 2021
Figure 1 for The AS-NU System for the M2VoC Challenge
Figure 2 for The AS-NU System for the M2VoC Challenge
Figure 3 for The AS-NU System for the M2VoC Challenge
Figure 4 for The AS-NU System for the M2VoC Challenge
Viaarxiv icon

Speech Recognition by Simply Fine-tuning BERT

Add code
Jan 30, 2021
Figure 1 for Speech Recognition by Simply Fine-tuning BERT
Figure 2 for Speech Recognition by Simply Fine-tuning BERT
Figure 3 for Speech Recognition by Simply Fine-tuning BERT
Figure 4 for Speech Recognition by Simply Fine-tuning BERT
Viaarxiv icon

Speech Enhancement with Zero-Shot Model Selection

Add code
Dec 17, 2020
Figure 1 for Speech Enhancement with Zero-Shot Model Selection
Figure 2 for Speech Enhancement with Zero-Shot Model Selection
Figure 3 for Speech Enhancement with Zero-Shot Model Selection
Figure 4 for Speech Enhancement with Zero-Shot Model Selection
Viaarxiv icon

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

Add code
Nov 09, 2020
Figure 1 for STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model
Figure 2 for STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model
Figure 3 for STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model
Figure 4 for STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model
Viaarxiv icon