# ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling

arXiv: https://arxiv.org/abs/2606.10233 · HTML: https://mlsanity.com/paper/2606.10233/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Efficient Neural Audio Synthesis](https://mlsanity.com/paper/1802.08435/) (2018)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition](https://mlsanity.com/paper/2010.10759/) (2020)
- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://mlsanity.com/paper/2503.01710/) (2025)
- [Streaming automatic speech recognition with the transformer model](https://mlsanity.com/paper/2001.02674/) (2020)
- [The VoiceMOS Challenge 2022](https://mlsanity.com/paper/2203.11389/) (2022)
- [Towards Frame-level Quality Predictions of Synthetic Speech](https://mlsanity.com/paper/2508.10374/) (2025)
- [UrgentMOS: Unified Multi-Metric and Preference Learning for Robust Speech Quality Assessment](https://mlsanity.com/paper/2601.18438/) (2026)
- [NOMAD: Unsupervised Learning of Perceptual Embeddings for Speech Enhancement and Non-matching Reference Audio Quality Assessment](https://mlsanity.com/paper/2309.16284/) (2023)
- [ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation](https://mlsanity.com/paper/2505.24518/) (2025)
- [Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization](https://mlsanity.com/paper/2509.15579/) (2025)

## Built on by (most cited first, 1 of 1)

- [TurnBench: A Multi-Domain Benchmark for Turn-Taking Dynamics in Spoken Dialogue](https://mlsanity.com/paper/2608.25218/) (2026)

## Abstract (arXiv)

While speech quality is typically assessed on complete utterances, streaming and generative systems require incremental estimation from partial audio. Existing predictors assume full context, degrading on prefix-constrained inputs. Extending ARECHO, we propose ANCHOR, reformulating incremental assessment as a multi-resolution autoregressive task. It models chunk- and utterance-level quality within a single decoder using dual-resolution tokens and a resolution-aware hierarchy for coarse-to-fine refinement. Experiments show substantial robustness under partial input, including a 48% PLCMOS error reduction on 2-second prefixes. Convergence analysis reveals a 4-6 s effective perceptual context horizon. A stress test further isolates structured extrapolation biases under localized corruption. Results demonstrate that hierarchical supervision improves incremental prediction and elucidates how perceptual quality accumulates over time.