ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation

TL;DR

ARECHO is a novel autoregressive system for multi-metric speech evaluation that models inter-metric dependencies, improving accuracy, interpretability, and reliability in diverse speech assessment tasks.

Contribution

It introduces a chain-based evaluation framework with a tokenization pipeline, dependency modeling, and confidence decoding for comprehensive speech quality assessment.

Findings

Outperforms baseline in diverse speech evaluation scenarios

Enhances interpretability through dependency modeling

Reduces error propagation with confidence-oriented decoding

Abstract

Speech signal analysis poses significant challenges, particularly in tasks such as speech quality evaluation and profiling, where the goal is to predict multiple perceptual and objective metrics. For instance, metrics like PESQ (Perceptual Evaluation of Speech Quality), STOI (Short-Time Objective Intelligibility), and MOS (Mean Opinion Score) each capture different aspects of speech quality. However, these metrics often have different scales, assumptions, and dependencies, making joint estimation non-trivial. To address these issues, we introduce ARECHO (Autoregressive Evaluation via Chain-based Hypothesis Optimization), a chain-based, versatile evaluation system for speech assessment grounded in autoregressive dependency modeling. ARECHO is distinguished by three key innovations: (1) a comprehensive speech information tokenization pipeline; (2) a dynamic classifier chain that explicitly captures inter-metric dependencies; and (3) a two-step confidence-oriented decoding algorithm that enhances inference reliability. Experiments demonstrate that ARECHO significantly outperforms the baseline framework across diverse evaluation scenarios, including enhanced speech analysis, speech generation evaluation, and, noisy speech evaluation. Furthermore, its dynamic dependency modeling improves interpretability by capturing inter-metric relationships. Across tasks, ARECHO offers reference-free evaluation using its dynamic classifier chain to support subset queries (single or multiple metrics) and reduces error propagation via confidence-oriented decoding.