cs.SDOct 30, 2026

Scalable Audio-LLM System for Speech MOS Evaluation: A Diagnostic Case Study and Adaptation Roadmap

Authors: Dimitrios Kokkinis, Panagiotis Kakoulidis, Nikolaos Ellinas, Chrysovalanti Lymperi, Alexandra Vioni, Georgios Vardaxoglou, Iakovi Alexiou, Myrsini Christidou, 

Organizations: Innoetics, Samsung Electronics, Greece · Mobile eXperience Business, Samsung Electronics, Republic of Korea

Abstract

The continuous deployment of enterprise voice systems creates a critical operational bottleneck: evaluating the acoustic quality of synthetic speech across high-volume production updates. While human Mean Opinion Score (MOS) remains the quality gold standard, it introduces severe operational costs and turn-around delays that make continuous integration infeasible. In this work, we present a system design case study for a scalable, low-cost and offline evaluation pipeline capable of scoring large batches of synthetic speech at marginal cost. First, we use Qwen2-Audio-7B-Instruct in a zero-shot setting for granular MOS estimation, noticing perceptual blind spots and inherent biases. Then, we analyze SOMOS dataset and construct a diagnostic benchmark that operationalizes two prosodic dimensions associated with human naturalness ratings. Finally, we adapt Qwen2-Audio-7B-Instruct through a parameter-efficient finetuning (LoRA) on the task of MOS evaluation, observing improvements over base model and widely used neural baselines like UTMOS and establishing a practical blueprint for enterprise-grade speech quality assurance.

Figures & tables

Explore similar work

CardsList
  1. Few-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language Models

    Apr 15, 2026Ryandhimas E. Zezario, Dyah A. M. G. Wisnu, Szu-Wei Fu +3Speech Quality Assessment

  2. Is Semantics Enough for Speech Mean Opinion Score Prediction?

    Sep 3, 2026Tianyu Lan, Yufei Shi, Yang Ai +3Human Preference EvaluationNeural Audio Codecs

  3. Investigating Human-Model Discrepancies in Speech Quality Assessment via Acoustic and Prosodic Perturbations

    Jun 18, 2026Masato Takagi, Masaya Kawamura, Reo Shimizu +1Human Preference EvaluationSpeech Generation Evaluation