Deep Denoising Auto-encoder for Statistical Speech Synthesis

2015/06/17 by Zhenhua Wu, Wu, Zhenzhou, Shinji Takaki +3
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing

paper · pdf · doi:10.48550/arxiv.1506.05268

openalex publication_date 2015/06/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper proposes a deep denoising auto-encoder technique to extract better acoustic features for speech synthesis. The technique allows us to automatically extract low-dimensional features from high dimensional spectral features in a non-linear, data-driven, unsupervised way. We compared the new stochastic feature extractor with conventional mel-cepstral analysis in analysis-by-synthesis and text-to-speech experiments. Our results confirm that the proposed method increases the quality of synthetic speech in both experiments.

Related

• A Deep Learning Approach to Data-driven Parameterizations for Statistical Parametric Speech Synthesis
• Statistical Parametric Speech Synthesis Using Bottleneck Representation From Sequence Auto-encoder
• Deep Vocoder: Low Bit Rate Compression of Speech with Deep Autoencoder
• High-Quality Vocoding Design with Signal Processing for Speech Synthesis and Voice Conversion
• Disentangling Speech and Non-Speech Components for Building Robust Acoustic Models from Found Data