Personalized Percepnet: Real-time, Low-complexity Target Voice Separation And Enhancement

Abstract

The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity. In this paper, we present Personalized PercepNet, a real-time speech enhancement model that separates a target speaker from a noisy multi-talker mixture without compromising on complexity of the recently proposed PercepNet. To enable speaker-dependent speech enhancement, we first show how we can train a perceptually motivated speaker embedder network to produce a representative embedding vector for the given speaker. Personalized PercepNet uses the target speaker embedding as additional information to pick out and enhance only the target speaker while suppressing all other competing sounds. Our experiments show that the proposed model significantly outperforms PercepNet and other baselines, both in terms of objective speech enhancement metrics and human opinion scores.

Stats

• citations28
• S2 citations—
• github stars0
• HF likes0
• heat score10.97
• arxiv keygiri2021personalized

Related papers

• Personalized Speech Enhancement Without A Separate Speaker Embedding Model (2024)5.24
• A Lightweight Dual-stage Framework For Personalized Speech Enhancement Based On Deepfilternet2 (2024)2.26
• Voicefilter: Targeted Voice Separation By Speaker-conditioned Spectrogram Masking (2018)17.48
• Real-time Joint Personalized Speech Enhancement And Acoustic Echo Cancellation (2022)4.52
• Percepnet+: A Phase And SNR Aware Percepnet For Real-time Speech Enhancement (2022)9.23
• Sef-pnet: Speaker Encoder-free Personalized Speech Enhancement With Local And Global Contexts Aggregation (2025)2.26
• Individualized Conditioning And Negative Distances For Speaker Separation (2022)2.26
• Real-time Speech Enhancement And Separation With A Unified Deep Neural Network For Single/dual Talker Scenarios (2023)2.26