Scaling phoneme-based TTS augmentation for ASR: A unified pipeline and controlled study

• URL: http://arxiv.org/abs/2608.26697v1
• Date: Thu, 27 Aug 2026 06:53:32 GMT
• Title: Scaling phoneme-based TTS augmentation for ASR: A unified pipeline and controlled study
• Abstract summary: We present a unified phoneme-based TTS-to-ASR augmentation pipeline built around a multilingual TTS model trained from scratch.<n>The pipeline combines language-specific grapheme-to-phoneme conversion, reference-speech filtering, candidate-text selection, synthesis, and matched ASR continuation.
• Score: 8.990924552624199
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Synthetic speech provides scalable supervision for automatic speech recognition (ASR), but its benefit depends on the selected texts, reference speech, and amount of synthesized data. We present a unified phoneme-based TTS-to-ASR augmentation pipeline built around a multilingual TTS model trained from scratch using the F5-TTS architecture with language-ID conditioning. The pipeline combines language-specific grapheme-to-phoneme conversion, reference-speech filtering, candidate-text selection, synthesis, and matched ASR continuation. We further propose phoneme-frequency-guided selection (PFGS), which ranks candidate sentences using phoneme frequencies estimated from real ASR training labels. Experiments with separate monolingual ASR systems for Arabic, French, Italian, and Portuguese span 13 test sets. Across the synthesis-scale sweep, random augmentation improves over matched real-only continuation on 11 test sets. Under a nominal 60% synthesis budget, PFGS improves over real-only training on 12 test sets and over random selection on 9. Its largest relative word error rate (WER) reduction against random selection is 19.3%. With target texts and synthesis counts fixed, reference-speech filtering reduces absolute WER by 0.29 and 0.59 points on Italian and French Common Voice, respectively. These results identify synthesis scale, candidate-text content, and reference quality as important control variables in TTS-based ASR augmentation.

Related papers

• VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation [35.0242994611344]
  VoiceTTA is a reinforcement learning-based test-time adaptation (TTA) method that improves voice imitation of pretrained zero-shot TTS models.<n>Experiments demonstrate substantial improvements on uncommon speech prompts, outperforming state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-25T02:18:24Z)
• Improving Code-Switching Speech Recognition with TTS Data Augmentation [58.34842693152991]
  This paper explores multilingual text-to-speech (TTS) models as an effective data augmentation technique to address this shortage.<n>We fine-tune the multilingual CosyVoice2 TTS model on the SEAME dataset to generate synthetic conversational Chinese-English code-switching speech.
  arXiv  Detail & Related papers  (2026-01-02T10:11:51Z)
• A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data [46.73430446242378]
  We propose a self-refining framework that enhances ASR performance with only unlabeled datasets.<n>We demonstrate the effectiveness of the framework on Taiwanese Mandarin speech.
  arXiv  Detail & Related papers  (2025-06-10T17:30:32Z)
• Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM [48.71951982716363]
  Text-to-speech (TTS) models have been widely adopted to enhance automatic speech recognition (ASR) systems. We propose Hard- Synth, a novel ASR data augmentation method that leverages large language models (LLMs) and advanced zero-shot TTS. Our approach employs LLMs to generate diverse in-domain text through rewriting, without relying on additional text data.
  arXiv  Detail & Related papers  (2024-11-20T09:49:37Z)
• Towards Selection of Text-to-speech Data to Augment ASR Training [20.115236045164355]
  We train a neural network to measure the similarity of a synthetic data to real speech. We find that incorporating synthetic samples with considerable dissimilarity to real speech is crucial for boosting recognition performance.
  arXiv  Detail & Related papers  (2023-05-30T17:24:28Z)
• Code-Switching Text Generation and Injection in Mandarin-English ASR [57.57570417273262]
  We investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T) We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explicitly by Text-To-Speech (TTS) conversion or implicitly by tying speech and text latent spaces. Experimental results on the T-T model trained with a dataset containing 1,800 hours of real Mandarin-English code-switched speech show that our approaches to inject generated code-switching text significantly boost the performance of T-T models.
  arXiv  Detail & Related papers  (2023-03-20T09:13:27Z)
• When Is TTS Augmentation Through a Pivot Language Useful? [26.084140117526488]
  We propose to produce synthetic audio by running text from the target language through a trained TTS system for a higher-resource pivot language. Using several thousand synthetic TTS text-speech pairs and duplicating authentic data to balance yields optimal results. Application of these findings improves ASR by 64.5% and 45.0% character error reduction rate (CERR) respectively for two low-resource languages.
  arXiv  Detail & Related papers  (2022-07-20T13:33:41Z)
• LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition [148.43282526983637]
  We develop LRSpeech, a TTS and ASR system for languages with low data cost. We conduct experiments on an experimental language (English) and a truly low-resource language (Lithuanian) to verify the effectiveness of LRSpeech. We are currently deploying LRSpeech into a commercialized cloud speech service to support TTS on more rare languages.
  arXiv  Detail & Related papers  (2020-08-09T08:16:33Z)
• You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation [59.31769998728787]
  We build our TTS system on an ASR training database and then extend the data with synthesized speech to train a recognition model. Our system establishes a competitive result for end-to-end ASR trained on LibriSpeech train-clean-100 set with WER 4.3% for test-clean and 13.5% for test-other.
  arXiv  Detail & Related papers  (2020-05-14T17:24:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.