Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2509.12974

The CCF AATC 2025 Speech Restoration Challenge: A Retrospective

Junan Zhang·Mengyao Zhu·Xin Xu·Hui Bu·Zhenhua Ling·Zhizheng Wu
View original source ↗Read source document ↗Export metadata ↓

Abstract

Real-world speech communication is rarely affected by a single type of degradation. Instead, it suffers from a complex interplay of acoustic interference, codec compression, and, increasingly, secondary artifacts introduced by upstream enhancement algorithms. To bridge the gap between academic research and these realistic scenarios, we introduced the CCF AATC 2025 Challenge. This challenge targets universal blind speech restoration, requiring a single model to handle three distinct distortion categories: acoustic degradation, codec distortion, and secondary processing artifacts. In this paper, we provide a comprehensive retrospective of the challenge, detailing the dataset construction, task design, and a systematic analysis of the 25 participating systems. We report three key findings that define the current state of the field: (1) Efficiency vs. Scale: Contrary to the trend of massive generative models, top-performing systems demonstrated that lightweight discriminative architectures (<10M parameters) can achieve state-of-the-art performance, balancing restoration quality with deployment constraints. (2) Generative Trade-off: While generative and hybrid models excel in theoretical perceptual metrics, breakdown analysis reveals they suffer from "reconstruction bias" in high-SNR codec tasks and struggle with hallucination in complex secondary artifact scenarios. (3) Metric Gap: Most critically, our rank correlation analysis exposes a strong negative correlation (\r{ho}=-0.8) between widely-used reference-free metrics (e.g., DNSMOS) and human MOS when evaluating hybrid systems. This indicates that current metrics may over-reward artificial spectral smoothness at the expense of perceptual naturalness. This paper aims to serve as a reference for future research in robust speech restoration and calls for the development of next-generation evaluation metrics sensitive to generative artifacts.

Explore related subjects

cs.SDeess.AS

Keep this discovery

BibTeXRIS

Junan Zhang, Mengyao Zhu, Xin Xu, Hui Bu, Zhenhua Ling, Zhizheng Wu. 2025-09-16. The CCF AATC 2025 Speech Restoration Challenge: A Retrospective. https://arxiv.org/abs/2509.12974

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗