supikiti/Awesome-tts-and-vc

Here is a summary of the conference papers we read.

Awesome-tts-and-vc

This is a repository for abstracts of international conference papers related to text-to-speech and voice conversion.

📚 Conference

• ICASSP2020
• INTERSPEECH2020

👥 Author

@supikiti, @YotaUedaa

📄 Papers

ICASSP2020

SPE-P3 - Machine Learning for Speech Synthesis I

• TRANSFORMER-BASED TEXT-TO-SPEECH WITH WEIGHTED FORCED ATTENTION
• SCALABLE MULTILINGUAL FRONTEND FOR TTS
• GERATING DIVERSE AND NATURAL TEXT-TO-SPEECH SAMPLES USING A QUANTIZED FINE-GRAINED VAE AND AUTOREGRESSIVE PROSODY PRIOR
• An Effective Style Token Weight Control Technique for End-to-End Emotional Speech Synthesis
• IMPROVING END-TO-END SPEECH SYNTHESIS WITH LOCAL RECURRENT NEURAL NETWORK ENHANCED TRANSFORMER

SPE-L8 - Speech Synthesis and Voice Conversion II

• TEACHER-STUDENT TRAINING FOR ROBUST TACOTRON-BASED TTS
• FULLY-HIERARCHICAL FINE-GRAINED PROSODY MODELING FOR INTERRETABLE SPEECH SYNTHESIS
• TRANSFERRING NEURAL SPEECH WAVEFORM SYNTHESIZERS TO MUSICAL
• F0-CONSYSTENT MANY-TO-MANY VOICE CONVERSION VIA CONDITIONAL AUTOENCODER
• Many-to-Many Voice Conversion using Conditional Cycle-Consistent Adversarial Networks
• END-TO-END ACCENT CONVERSION WITHOUT USING NATIVE UTTERANCES

SPE-P21 - Voice Conversion

• ONE-SHOT VOICE CONVERSION USING STAR-GAN
• ONE-SHOT VOICE CONVERSION BY VECTOR QUANTIZATION

Others

• One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization
• Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
• Scalable Factorized Hierarchical Variational Autoencoder Training
• Investigation of using disentangled and interpretable representations for one-shot cross-lingual voice conversion
• EXPLORING SPEECH ENHANCEMENT WITH GENERATIVE ADVERSARIAL NETWORKS FOR ROBUST SPEECH RECOGNITION
• MTGAN-Speaker_Verification_through_Multitasking_Triplet_Generative_Adversarial_Network