Article

A Multi-Task Learning Speech Synthesis Optimization Method Based on CWT: A Case Study of Tacotron2

2023-10-11

Abstract excerpt

<title>Abstract</title> <p>Text-to-speech (TTS) synthesis plays an essential role in human-computer interaction. Currently, the vast majority of TTS acoustic models select only the Mel spectrum as an intermediate feature from text to speech. However, the resulting Mel spectrograms can be ambiguous in some aspects due to the poor ability of the Fourier transform to capture the mutation signal during the acquisitio...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: ab79c5c4-a30d-5024-a113-0242007cc79f
DOI: 10.21203/rs.3.rs-3369751/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

A Multi-Task Learning Speech Synthesis Optimization Method Based on CWT: A Case Study of Tacotron2DOI 10.21203/rs.3.rs-3369751/v1Read

A Intelligent Speech Recognition Method Based on Stable LearningSemantic proximity Read

Speech Enhancement, Databases, Features and Classifiers in Automatic Speech Recognition: A ReviewSemantic proximity Read

Learning Emotional Nuances in Speech via DCNNs and Spectral Feature IntegrationSemantic proximity Read

Creating Speech Synthesis Process by Using Pulse Model in Log-Domain Vocoder With Whale Optimized Deep Convolution Neural NetworksSemantic proximity Read

HSERNet: Hybrid Speech Emotion Recognition using Conformer-Convolutional Neural NetworksSemantic proximity Read

Speaker-Aware Simulation Improves Conversational Speech RecognitionSemantic proximity Read

Expressive Speech Synthesis by Modeling Prosody with Variational Autoencoders for Bangla Text-to-SpeechSemantic proximity Read

Enhancing Arabic Speech Therapy with AI: A Specialized AI-Based System for Arabic Stuttering ClassificationSemantic proximity Read

ViTone: A Diagnostic Benchmark for Tonal Faithfulness in Vietnamese Text-to-SpeechSemantic proximity Read

FedSER-XAI: PSO-Optimized Multi-StreamCross-Attention Transformer with Graph Featuresfor Explainable Federated Speech EmotionRecognitioneSemantic proximity Read

Bangla Speech Emotion Recognition Using Deep Learning-Based Ensemble Learning and Feature FusionSemantic proximity Read

Fake Voice Detection: A Comparative Analysis of Complex-Valued Deep Learning and Transformer Models across Multiple LanguagesSemantic proximity Read