mlsanityData to 7 Oct 2026

Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems

arXiv 1912.09257 ↗First posted 19 Dec 2019cs.CL cs.LG eess.AScited by 46

Not on the map. Why?

Abstract (arXiv)

Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS system trained only on the ASR corpora itself. ASR and TTS systems are built separately to show that text-only data can be used to enhance existing end-to-end ASR systems without the necessity of parameter or architecture changes. We compare our method with language model integration of the same text data and with simple data augmentation methods like SpecAugment and show that performance improvements are mostly independent. We achieve improvements of up to 33% relative in word-error-rate (WER) over a strong baseline with data-augmentation in a low-resource environment (LibriSpeech-100h), closing the gap to a comparable oracle experiment by more than 50%. We also show improvements of up to 5% relative WER over our most recent ASR baseline on LibriSpeech-960h.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 6; 2023: 13; 2024: 12; 2025: 2; 2026: 4.

46 papers.

Sort:

By area:

  1. 2023StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learnerscited by 177
  2. 2023Scaling Laws of Synthetic Images for Model Training ... for Nowcited by 107
  3. 2023Learning Vision from Models Rivals Learning Vision from Datacited by 71
  4. 2024SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?cited by 64
  5. 2023AudioChatLlama: Towards General-Purpose Speech Abilities for LLMscited by 59
  6. 2021SynthASR: Unlocking Synthetic Data for Speech Recognitioncited by 34
  7. 2023Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentationcited by 30
  8. 2021Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognitioncited by 24
  9. 2024FlashSpeech: Efficient Zero-Shot Speech Synthesiscited by 22
  10. 2021EAT: Enhanced ASR-TTS for Self-supervised Speech Recognitioncited by 13
  11. 2025Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Datacited by 12
  12. 2022Synthesizing Dysarthric Speech Using Multi-talker TTS for Dysarthric Speech Recognitioncited by 10
34 more
  1. 2024Krey`ol-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languagescited by 10
  2. 2021On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASRcited by 9
  3. 2023Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesiscited by 9
  4. 2024Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognitioncited by 9
  5. 2021Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architecturescited by 8
  6. 2022USTED: Improving ASR with a Unified Speech and Text Encoder-Decodercited by 7
  7. 2022Learning Speech Emotion Representations in the Quaternion Domaincited by 7
  8. 2022A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Datacited by 7
  9. 2022When Is TTS Augmentation Through a Pivot Language Useful?cited by 7
  10. 2023Accurate synthesis of Dysarthric Speech for ASR data augmentationcited by 7
  11. 2022Text-To-Speech Data Augmentation for Low Resource Speech Recognitioncited by 6
  12. 2021Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptationcited by 4
  13. 2023On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognitioncited by 4
  14. 2024Learning from Synthetic Data for Visual Groundingcited by 4
  15. 2023Cross-Corpora Spoken Language Identification with Domain Diversification and Generalizationcited by 3
  16. 2023SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chaincited by 2
  17. 2024High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASRcited by 2
  18. 2023Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognitioncited by 1
  19. 2024Contrastive Learning from Synthetic Audio Doppelg"angerscited by 1
  20. 2024Handling Numeric Expressions in Automatic Speech Recognitioncited by 1
  21. 2026How to Leverage Synthetic Speech for LLM-Based ASR Systems?cited by 1
  22. 2021Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformerscited by 0
  23. 2021Analysis of Data Augmentation Methods for Low-Resource Maltese ASRcited by 0
  24. 2021Sequence-level self-learning with multiple hypothesescited by 0
  25. 2023MAC: A unified framework boosting low resource automatic speech recognitioncited by 0
  26. 2023End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representationscited by 0
  27. 2024Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASRcited by 0
  28. 2024Written Term Detection Improves Spoken Term Detectioncited by 0
  29. 2024Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Spacecited by 0
  30. 2024Beyond Oversmoothing: Evaluating DDPM and MSE for Scalable Speech Synthesis in ASRcited by 0
  31. 2025Voice Cloning for Dysarthric Speech Synthesis: Addressing Data Scarcity in Speech-Language Pathologycited by 0
  32. 2026Elderly-Contextual Data Augmentation via Speech Synthesis for Elderly ASRcited by 0
  33. 2026Text-Utilization for Encoder-dominated Speech Recognition Modelscited by 0
  34. 2026When Synthetic Speech Is All You Have: Better Call GRPOcited by 0