Skip to content

Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures

Sep 2026 · arXiv.org · Vol abs/2609.28974 · 0 citations · 32 references
Engineering Computer Science

TL;DR

This work evaluates PTQ across TTS architectures under one protocol with three core models, weight and activation ablations of eight more, and two held-out models quantized blind.

Abstract

Post-training quantization (PTQ) reduces the cost of on-device text-to-speech (TTS), but published evaluations cover one system or method. We evaluate PTQ across TTS architectures under one protocol with three core models, weight and activation ablations of eight more, and two held-out models quantized blind. Four-bit per-channel weights reduce UTMOS, a predicted mean opinion score, by 2.8 on Supertonic and 0.07 on Kokoro, and per-tensor scaling can cause severe degradation even at 8 bits. The same bit width yields different outcomes, because the sensitive component is model-specific and not reliably predicted from the model class. A staged ablation procedure identifies it, and per-layer GPTQ can restore it to within 0.1 UTMOS. Real int8 and int4 kernels reproduce the simulated ordering at hardware-dependent cost. On a Mac mini, a 4-bit weight kernel runs Supertonic at 0.60x the fp32 latency while int8 is slower, so each configuration requires validation on the target runtime.

View source

Similar papers

Sep 2026

Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality

The Channel-wise Token-balanced Output-Aware Clipping (CTOAC) method, which learns per-input-channel clipping bounds by minimizing a token-balanced reconstruction loss on the corresponding linear outputs, is proposed.

Jonghyeon Lim, Changhoon Yim · 0 citations
Sep 2026

GenTraceBench: A Benchmark for Tracing Audio Deepfakes Across Pre- and Post-training Stages

Modern text-to-speech (TTS) systems are rarely deployed as unchanged pre-trained models. They are often adapted through supervised fine-tuning (SFT) or preference optimization such as DPO and GRPO. This raises a practical question for audio deepfake forensics: do fingerprints learned from a foundation generator remain...

Li Wang, Kun-Yu Feng, Wan Lin et al. · 0 citations
#natural language process... Preprint Sep 2026

Text Scores Do Not Establish Performance on Lexically Non-Diagnostic Speech Tasks: A Qwen2-Audio Quantization Case Study

Text-output scores alone do not show whether quantization preserves performance on speech tasks whose target labels cannot be recovered from the transcript. We evaluate fixed mixed 4/8-bit Qwen2-Audio-7B-Instruct allocations averaging 6 and 7 bits per parameter on 508 English-to-German FLEURS utterances and on 512 RAVD...

Meng-Zhe Geng, Jin-Xin Ji, Jun-Hao Xu · 0 citations
#artificial intelligence Preprint Sep 2026

All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs

All for 1-Bit (AF1) is proposed, a genuine 1-bit PTQ framework for LLMs that consistently outperforms existing binarization-based PTQ methods in perplexity and zero-shot accuracy, providing a practical path toward deployable genuine 1-bit compression for LLMs.

Zhi-Xiong Zhao, Zu-Kang Xu, Guang-Yu Sun et al. · 4 citations
#artificial intelligence Preprint Oct 2026

OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models

Quantization-aware training (QAT) can recover much of the accuracy lost when large language models are compressed below four bits. Existing re- covery stages, however, are commonly optimized on fixed completions or teacher-generated answers, whereas the deployed quantized model condi- tions on prefixes generated by its...

Wen-Jun Wang, He-Ping Li, Yang-Gan Gu et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.