292 results on '"Hsin-Min Wang"'
Search Results
2. SpeechCLIP+: Self-Supervised Multi-Task Representation Learning for Speech Via Clip and Speech-Image Data.
3. Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model.
4. Audio-Visual Mandarin Electrolaryngeal Speech Voice Conversion.
5. A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech.
6. Mandarin Electrolaryngeal Speech Voice Conversion using Cross-domain Features.
7. The Voicemos Challenge 2023: Zero-Shot Subjective Speech Quality Prediction for Multiple Domains.
8. LC4SV: A Denoising Framework Learning to Compensate for Unseen Speaker Verification Models.
9. MTI-Net: A Multi-Target Speech Intelligibility Prediction Model.
10. NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling.
11. Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks.
12. Chain-based Discriminative Autoencoders for Speech Recognition.
13. The VoiceMOS Challenge 2022.
14. MBI-Net: A Non-Intrusive Multi-Branched Speech Intelligibility Prediction Model for Hearing Aids.
15. EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement.
16. Partially Fake Audio Detection by Self-Attention-Based Fake Span Discovery.
17. Speech-enhanced and Noise-aware Networks for Robust Speech Recognition.
18. Is Character Trigram Overlapping Ratio Still the Best Similarity Measure for Aligning Sentences in a Paraphrased Corpus?
19. Chinese Movie Dialogue Question Answering Dataset.
20. D4AM: A General Denoising Framework for Downstream Acoustic Models.
21. Relational Data Selection for Data Augmentation of Speaker-Dependent Multi-Band MelGAN Vocoder.
22. Dual-Path Filter Network: Speaker-Aware Modeling for Speech Separation.
23. A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion.
24. AlloST: Low-Resource Speech Translation Without Source Transcription.
25. Speech Enhancement with Zero-Shot Model Selection.
26. Mandarin Electrolaryngeal Speech Voice Conversion with Sequence-to-Sequence Modeling.
27. HASA-Net: A Non-Intrusive Hearing-Aid Speech Assessment Network.
28. Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving.
29. Investigation of a Single-Channel Frequency-Domain Speech Enhancement Network to Improve End-to-End Bengali Automatic Speech Recognition Under Unseen Noisy Conditions.
30. Melody Harmonization Using Orderless Nade, Chord Balancing, and Blocked Gibbs Sampling.
31. Speech Recognition by Simply Fine-Tuning Bert.
32. Generation of Speaker Representations Using Heterogeneous Training Batch Assembly.
33. Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion.
34. Improvement of Spatial Ambiguity in Multi-Channel Speech Separation Using Channel Attention.
35. SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours.
36. MoEVC: A Mixture of Experts Voice Conversion System With Sparse Gating Mechanism for Online Computation Acceleration.
37. Mining Commonsense and Domain Knowledge from Math Word Problems.
38. A Flexible and Extensible Framework for Multiple Answer Modes Question Answering.
39. SERIL: Noise Adaptive Speech Enhancement Using Regularization-Based Incremental Learning.
40. Lite Audio-Visual Speech Enhancement.
41. Using Taigi Dramas with Mandarin Chinese Subtitles to Improve Taigi Speech Recognition.
42. Statistics Pooling Time Delay Neural Network Based on X-Vector for Speaker Verification.
43. Self-Supervised Denoising Autoencoder with Linear Regression Decoder for Speech Enhancement.
44. Combining Deep Embeddings of Acoustic and Articulatory Features for Speaker Identification.
45. STOI-Net: A Deep Learning based Non-Intrusive Speech Intelligibility Assessment Model.
46. Joint Training of Guided Learning and Mean Teacher Models for Sound Event Detection.
47. Generalization of Spectrum Differential based Direct Waveform Modification for Voice Conversion.
48. Specialized Speech Enhancement Model Selection Based on Learned Non-Intrusive Quality Assessment Metric.
49. Investigation of F0 Conditioning and Fully Convolutional Networks in Variational Autoencoder Based Voice Conversion.
50. MOSNet: Deep Learning-Based Objective Assessment for Voice Conversion.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.