Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2509.17021

Bridging the gap between training and inference in LM-based TTS models

Ruonan Zhang·Lingzhou Mu·Xixin Wu·Kai Zhang
View original source ↗Read source document ↗Export metadata ↓

Abstract

Recent advancements in text-to-speech (TTS) have shown that language model (LM) based systems offer competitive performance compared to traditional approaches. However, in training, TTS models use ground-truth (GT) tokens as prefixes to predict the next token, while in inference these tokens are not available, a gap between training and inference that is often neglected. In this study, we propose a prompt-guided hybrid training scheme to mitigate exposure bias in popular LM-based TTS systems. Our core idea is to adopt a hybrid training paradigm that combines teacher forcing with free running, thereby introducing self-generated tokens into the training process. This makes the training mode more consistent with inference, reducing the training-inference gap. In addition, we incorporate an EOS prediction mechanism during training to detect incorrect sequence termination and adaptively control the free running process. Experimental results provide a comprehensive evaluation of the impact of exposure bias on LM-based TTS, and demonstrate that our method effectively narrows the training-inference gap, thereby improving the quality of synthesized long-form speech.

Explore related subjects

cs.SDeess.AS

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Ruonan Zhang, Lingzhou Mu, Xixin Wu, Kai Zhang. 2025-09-21. Bridging the gap between training and inference in LM-based TTS models. https://arxiv.org/abs/2509.17021

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↗