slt 2021

Audio Albert: A Lite Bert For Self-Supervised Learning Of Audio Representation

Domain Generalization With Triplet Network For Cross-Corpus Speech Emotion Recognition

Innovative Bert-Based Reranking Language Models For Speech Recognition

Fine-Grained Emotion Strength Transfer, Control And Prediction For Emotional Speech Synthesis

Detection And Evaluation Of Human And Machine Generated Speech In Spoofing Attacks On Automatic Speaker Verification Systems

Improved Parallel Wavegan Vocoder With Perceptually Weighted Spectrogram Loss

An Exploration Of Log-Mel Spectrogram And Mfcc Features For Alzheimers Dementia Recognition From Spontaneous Speechan Exploration Of Log-Mel Spectrogram And Mfcc Features For Alzheimers Dementia Recognition From Spontaneous Speech

Defending Your Voice: Adversarial Attack On Voice Conversion

Analysis Of Multimodal Features For Speaking Proficiency Scoring In An Interview Dialogue

Hierarchical Prosody Modeling For Non-Autoregressive Speech Synthesis

Unsupervised Acoustic-To-Articulatory Inversion Neural Network Learning Based On Deterministic Policy Gradient

Discriminative Neural Clustering For Speaker Diarisation