Papers
arxiv:2505.15380

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding

Published on Jun 3, 2025
Authors:
,
,
,
,
,
,

Abstract

Speech Speculative Decoding accelerates autoregressive speech synthesis by using a lightweight draft model to generate candidates verified in parallel by the target model, achieving 1.4x speedup with maintained quality.

AI-generated summary

Modern autoregressive speech synthesis models leveraging language models have demonstrated remarkable performance. However, the sequential nature of next token prediction in these models leads to significant latency, hindering their deployment in scenarios where inference speed is critical. In this work, we propose Speech Speculative Decoding (SSD), a novel framework for autoregressive speech synthesis acceleration. Specifically, our method employs a lightweight draft model to generate candidate token sequences, which are subsequently verified in parallel by the target model using the proposed SSD framework. Experimental results demonstrate that SSD achieves a significant speedup of 1.4x compared with conventional autoregressive decoding, while maintaining high fidelity and naturalness. Subjective evaluations further validate the effectiveness of SSD in preserving the perceptual quality of the target model while accelerating inference.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2505.15380
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2505.15380 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2505.15380 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2505.15380 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.