Flowvocoder: A Small Footprint Neural Vocoder Based Normalizing Flow For Speech Synthesis

Abstract

Recently, autoregressive neural vocoders have provided remarkable performance in generating high-fidelity speech and have been able to produce synthetic speech in real-time. However, autoregressive neural vocoders such as WaveFlow are capable of modeling waveform signals from mel-spectrogram, its number of parameters is significant to deploy on edge devices. Though NanoFlow, which has a small number of parameters, is a state-of-the-art autoregressive neural vocoder, the performance of NanoFlow is marginally lower than WaveFlow. Therefore, we propose a new type of autoregressive neural vocoder called FlowVocoder, which has a small memory footprint and is capable of generating high-fidelity audio in real-time. Our proposed model improves the density estimation of flow blocks by utilizing a mixture of Cumulative Distribution Functions (CDF) for bipartite transformation. Hence, the proposed model is capable of modeling waveform signals, while its memory footprint is much smaller than WaveF

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyluong2021flowvocoder

Related papers

• Audio Dequantization For High Fidelity Audio Generation In Flow-based Neural Vocoder (2020)6.77
• Flowavenet : A Generative Flow For Raw Audio (2018)0.00
• Voiceflow: Efficient Text-to-speech With Rectified Flow Matching (2023)0.00
• Fbwave: Efficient And Scalable Neural Vocoders For Streaming Text-to-speech On The Edge (2020)0.00
• Text-free Non-parallel Many-to-many Voice Conversion Using Normalising Flows (2022)7.16
• Flowtron: An Autoregressive Flow-based Generative Network For Text-to-speech Synthesis (2020)5.91
• V2sflow: Video-to-speech Generation With Speech Decomposition And Rectified Flow (2024)8.52
• Improving The Expressiveness Of Neural Vocoding With Non-affine Normalizing Flows (2021)0.00