Streaming Voice Conversion Via Intermediate Bottleneck Features And Non-streaming Teacher Guidance

TL;DR

This paper introduces a novel streaming voice conversion method using intermediate bottleneck features and a non-streaming teacher guidance framework, significantly improving naturalness, content consistency, and timbre similarity over previous systems.

Contribution

It replaces PPGs with IBFs for better prosody retention and employs a teacher guidance framework to reduce timbre leakage in streaming VC.

Findings

Achieved state-of-the-art naturalness score of 3.85

Improved content consistency to 3.77

Enhanced timbre similarity to 3.77

Abstract

Streaming voice conversion (VC) is the task of converting the voice of one person to another in real-time. Previous streaming VC methods use phonetic posteriorgrams (PPGs) extracted from automatic speech recognition (ASR) systems to represent speaker-independent information. However, PPGs lack the prosody and vocalization information of the source speaker, and streaming PPGs contain undesired leaked timbre of the source speaker. In this paper, we propose to use intermediate bottleneck features (IBFs) to replace PPGs. VC systems trained with IBFs retain more prosody and vocalization information of the source speaker. Furthermore, we propose a non-streaming teacher guidance (TG) framework that addresses the timbre leakage problem. Experiments show that our proposed IBFs and the TG framework achieve a state-of-the-art streaming VC naturalness of 3.85, a content consistency of 3.77, and a timbre similarity of 3.77 under a future receptive field of 160 ms which significantly outperform previous streaming VC systems.