Improving Trajectory Modelling For Dnn-based Speech Synthesis By Using Stacked Bottleneck Features And Minimum Generation Error Training

Abstract

We propose two novel techniques --- stacking bottleneck features and minimum generation error training criterion --- to improve the performance of deep neural network (DNN)-based speech synthesis. The techniques address the related issues of frame-by-frame independence and ignorance of the relationship between static and dynamic features, within current typical DNN-based synthesis frameworks. Stacking bottleneck features, which are an acoustically--informed linguistic representation, provides an efficient way to include more detailed linguistic context at the input. The minimum generation error training criterion minimises overall output trajectory error across an utterance, rather than minimising the error per frame independently, and thus takes into account the interaction between static and dynamic features. The two techniques can be easily combined to further improve performance. We present both objective and subjective results that demonstrate the effectiveness of the proposed tec

Stats

• citations23
• S2 citations—
• github stars0
• HF likes0
• heat score10.35
• arxiv keywu2016improving

Related papers

• Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks (2017)16.21
• Statistical Parametric Speech Synthesis Using Bottleneck Representation From Sequence Auto-encoder (2016)0.00
• Deep Feed-forward Sequential Memory Networks For Speech Synthesis (2018)5.84
• Low-latency Speech Enhancement Via Speech Token Generation (2023)7.50
• Generative Adversarial Network-based Glottal Waveform Model For Statistical Parametric Speech Synthesis (2019)10.35
• Sequence Training Of DNN Acoustic Models With Natural Gradient (2018)5.24
• Singing Voice Synthesis Based On Convolutional Neural Networks (2019)0.00
• Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework (2017)10.21