AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting

Sungwon Kim, Kevin J. Shih, Rohan Badlani, Joao Felipe Santos, Evelina Bakhturina, Mikyas T. Desta, Rafael Valle, Sungroh Yoon, Bryan Catanzaro

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Neural text-to-speech synthesis · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace fixed-size speaker embedding with speech prompt in text encoder (ablation)P-Flow · LibriSpeech test-cleanSECS: 0.373 -> 0.544Improved
replace fixed-size speaker embedding with speech prompt in text encoder (ablation)P-Flow · LibriSpeech test-cleanWER: 2.9 -> 2.6No clear effect
remove classifier-free guidance (gamma 1 -> 0) (ablation)P-Flow · LibriSpeech test-cleanWER: 2.6 -> 3.7Hurt
remove classifier-free guidance (gamma 1 -> 0) (ablation)P-Flow · LibriSpeech test-cleanSECS: 0.544 -> 0.492Hurt
increase guidance scale from 1 to 2 (ablation)P-Flow · LibriSpeech test-cleanSECS: 0.544 -> 0.546No clear effect
reduce Euler steps from 10 to 1 (ablation)P-Flow · LibriSpeech test-cleanSECS: 0.544 -> 0.420Hurt
reduce Euler steps from 10 to 2 (ablation)P-Flow · LibriSpeech test-cleanWER: 2.6 -> 2.9Hurt
increase Euler steps from 10 to 20 (ablation)P-Flow · LibriSpeech test-cleanSECS: 0.544 -> 0.540No clear effect
increase Euler steps from 1 to 20 (ablation)P-Flow · LibriSpeechMOS: 3.55 -> 4.14Improved
use Heun's second-order method with 4 steps instead of 10 Euler steps (ablation)P-Flow · LibriSpeech test-cleanSECS: 0.544 -> 0.552Improved
use midpoint method with 4 steps instead of 10 Euler steps (ablation)P-Flow · LibriSpeech test-cleanSECS: 0.544 -> 0.540No clear effect
P-Flow vs VALL-E in latencyP-Flow · LibriSpeechinference latency (s): 2.515 -> 0.115Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy