mlsanityData to 14 Oct 2026

LibriSpeech-PC: Benchmark for Evaluation of Punctuation and Capitalization Capabilities of end-to-end ASR Models

arXiv 2310.02943 ↗First posted 4 Oct 2023cs.CLcited by 49

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Traditional automatic speech recognition (ASR) models output lower-cased words without punctuation marks, which reduces readability and necessitates a subsequent text processing model to convert ASR transcripts into a proper format. Simultaneously, the development of end-to-end ASR models capable of predicting punctuation and capitalization presents several challenges, primarily due to limited data availability and shortcomings in the existing evaluation methods, such as inadequate assessment of punctuation prediction. In this paper, we introduce a LibriSpeech-PC benchmark designed to assess the punctuation and capitalization prediction capabilities of end-to-end ASR models. The benchmark includes a LibriSpeech-PC dataset with restored punctuation and capitalization, a novel evaluation metric called Punctuation Error Rate (PER) that focuses on punctuation marks, and initial baseline models. All code, data, and models are publicly available.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 13 of its 21 references that are in the map. First posted on arXiv 4 Oct 2023.

Builds on

13 of 21 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
  6. 2021What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpuscited by 80
  7. 2018Punctuation Prediction Model for Conversational Speechcited by 20
  8. 2020Multimodal Semi-supervised Learning Framework for Punctuation Prediction in Conversational Speechcited by 18
  9. 2019Fast and Accurate Capitalization and Punctuation for Automatic Speech Recognition Using Transformer and Chunk Mergingcited by 14
  10. 2021Capitalization and Punctuation Restoration: a Surveycited by 13
  11. 2021Golos: Russian Dataset for Speech Researchcited by 9
  12. 2022End-to-end Speech-to-Punctuated-Text Recognitioncited by 8
1 more
  1. 2020End to End ASR System with Automatic Punctuation Insertioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 18; 2026: 25.

49 papers.

Sort:

By area:

  1. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  2. 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generationcited by 57
  3. 2025ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matchingcited by 30
  4. 2026OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Modelscited by 25
  5. 2024Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASRcited by 6
  6. 2026PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMscited by 6
  7. 2026The Design Space of Tri-Modal Masked Diffusion Modelscited by 6
  8. 2025DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generationcited by 5
  9. 2025Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Samplingcited by 5
  10. 2025Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesiscited by 5
  11. 2024Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translationcited by 4
  12. 2025Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignmentcited by 4
37 more
  1. 2025Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generationcited by 4
  2. 2025DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generationcited by 3
  3. 2026VoXtream2: Full-stream TTS with dynamic speaking rate controlcited by 3
  4. 2026Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTScited by 3
  5. 2024Beyond Levenshtein: Leveraging Multiple Algorithms for Robust Word Error Rate Computations And Granular Error Classificationscited by 2
  6. 2025SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translationcited by 2
  7. 2025Length-Aware Rotary Position Embedding for Text-Speech Alignmentcited by 2
  8. 2026Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformerscited by 2
  9. 2026Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLMcited by 2
  10. 2023End-to-end Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training Datacited by 1
  11. 2025Efficient Speech Language Modeling via Energy Distance in Continuous Latent Spacecited by 1
  12. 2025Computational Narrative Understanding for Expressive Text-to-Speechcited by 1
  13. 2025DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibrationcited by 1
  14. 2025Vox-Evaluator: Enhancing Stability and Fidelity for Zero-shot TTS with A Multi-Level Evaluatorcited by 1
  15. 2026ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inferencecited by 1
  16. 2026WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modelingcited by 1
  17. 2026Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioningcited by 1
  18. 2026DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speechcited by 1
  19. 2026Depth through recurrence: Looped transformers for flow-matching TTScited by 1
  20. 2024Whispy: Adapting STT Whisper Models to Real-Time Environmentscited by 0
  21. 2025Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languagescited by 0
  22. 2025WhisperRT -- Turning Whisper into a Causal Streaming Modelcited by 0
  23. 2025Accelerating Diffusion Transformer-Based Text-to-Speech with Transformer Layer Cachingcited by 0
  24. 2025Enhancing Fully Formatted End-to-End Speech Recognition with Knowledge Distillation via Multi-Codebook Vector Quantizationcited by 0
  25. 2026PoDAR: Power-Disentangled Audio Representation for Generative Modelingcited by 0
  26. 2026Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representationcited by 0
  27. 2026Pixel-TTS: Image based Text Rendering for Robust Text-to-Speechcited by 0
  28. 2026OpenWER: Improving Cross-Lingual ASR Evaluation and Enabling Token-Based Accuracy Metricscited by 0
  29. 2026Best-of-N TTS Evaluation is Confounded by ASR Family Alignmentcited by 0
  30. 2026ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matchingcited by 0
  31. 2026SonicWeave: Chunk-Routed Mixture-of-Experts for Unified Audio Scene Generationcited by 0
  32. 2026Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenizationcited by 0
  33. 2026VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognitioncited by 0
  34. 2026Structured Claim-Level Discourse Representations for Dense Health Narrativescited by 0
  35. 2026ReaFlow-TTS: Realization-Conditioned Flow Matching for High-Quality and Controllable Speech Synthesiscited by 0
  36. 2026Multimodal Co-Generation With Continuous Bitstream Diffusioncited by 0
  37. 2026Fish Audio Drama 3 Technical Reportcited by 0