mlsanityData to 14 Oct 2026

Achieving Human Parity in Conversational Speech Recognition

arXiv 1610.05256 ↗First posted 17 Oct 2016cs.CL eess.AScited by 63

Not on the map. Why?

Abstract (arXiv)

Conversational speech recognition has served as a flagship speech recognition task since the release of the Switchboard corpus in the 1990s. In this paper, we measure the human error rate on the widely used NIST 2000 test set, and find that our latest automated system has reached human parity. The error rate of professional transcribers is 5.9% for the Switchboard portion of the data, in which newly acquainted pairs of people discuss an assigned topic, and 11.3% for the CallHome portion where friends and family members have open-ended conversations. In both cases, our automated system establishes a new state of the art, and edges past the human benchmark, achieving error rates of 5.8% and 11.0%, respectively. The key to our system's performance is the use of various convolutional and LSTM acoustic model architectures, combined with a novel spatial smoothing method and lattice-free MMI acoustic training, multiple recurrent neural network language modeling approaches, and a systematic use of system combination.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Oct 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 12; 2023: 11; 2024: 13; 2025: 4; 2026: 4.

63 papers.

Sort:

By area:

  1. 2021On Feature Decorrelation in Self-Supervised Learningcited by 160
  2. 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 124
  3. 2021UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Datacited by 77
  4. 2022Robust Self-Supervised Audio-Visual Speech Recognitioncited by 75
  5. 2022Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregationcited by 52
  6. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  7. 2021DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memoriescited by 42
  8. 2021QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpuscited by 38
  9. 2022A Survey of Multilingual Models for Automatic Speech Recognitioncited by 21
  10. 2025The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Datasetcited by 17
  11. 2021Transformer Language Models with LSTM-based Cross-utterance Information Representationcited by 15
  12. 2022Online Continual Learning of End-to-End Speech Recognition Modelscited by 15
38 more
  1. 2021Arabic Speech Recognition by End-to-End, Modular Systems and Humancited by 12
  2. 2021Accented Speech Recognition: A Surveycited by 12
  3. 2022Lethal Dose Conjecture on Data Poisoningcited by 12
  4. 2023Beating Backdoor Attack at Its Own Gamecited by 11
  5. 2021Dompteur: Taming Audio Adversarial Examplescited by 10
  6. 2021The History of Speech Recognition to the Year 2030cited by 10
  7. 2024MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognitioncited by 9
  8. 2021Cross-utterance Reranking Models with BERT and Graph Convolutional Networks for Conversational Speech Recognitioncited by 7
  9. 2021Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speechcited by 5
  10. 2023Multilingual Word Error Rate Estimation: e-WER3cited by 5
  11. 2024Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intentscited by 5
  12. 2022Survey on the Convergence of Machine Learning and Blockchaincited by 4
  13. 2022Toward Zero Oracle Word Error Rate on the Switchboard Benchmarkcited by 4
  14. 2024Enhancing Lip Reading with Multi-Scale Video and Multi-Encodercited by 4
  15. 2024Focus Agent: LLM-Powered Virtual Focus Groupcited by 4
  16. 2021Dialectal Speech Recognition and Translation of Swiss German Speech to Standard German Text: Microsoft's Submission to SwissText 2021cited by 3
  17. 2021User-Initiated Repetition-Based Recovery in Multi-Utterance Dialogue Systemscited by 3
  18. 2024Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNetcited by 3
  19. 2021GPU-Accelerated Forward-Backward algorithm with Application to Lattice-Free MMIcited by 2
  20. 2021VoiceMoji: A Novel On-Device Pipeline for Seamless Emoji Insertion in Dictationcited by 2
  21. 2024Backdoor Defense through Self-Supervised and Generative Learningcited by 2
  22. 2024Deep CLAS: Deep Contextual Listen, Attend and Spellcited by 2
  23. 2025Dealing with the Hard Facts of Low-Resource African NLPcited by 2
  24. 2026The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100cited by 2
  25. 2021Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attackscited by 1
  26. 2022DeepSketch: A New Machine Learning-Based Reference Search Technique for Post-Deduplication Delta Compressioncited by 1
  27. 2022An Investigation of Smart Contract for Collaborative Machine Learning Model Trainingcited by 1
  28. 2023Factual Consistency Oriented Speech Recognitioncited by 1
  29. 2023Cascading Hierarchical Networks with Multi-task Balanced Loss for Fine-grained hashingcited by 1
  30. 2023On Practical Aspects of Aggregation Defenses against Data Poisoning Attackscited by 1
  31. 2023A Glance is Enough: Extract Target Sentence By Looking at A keywordcited by 1
  32. 2023Iterative Shallow Fusion of Backward Language Model for End-to-End Speech Recognitioncited by 1
  33. 2025Automatic Speech Recognition for Non-Native English: Accuracy and Disfluency Handlingcited by 1
  34. 2021Exploiting Beam Search Confidence for Energy-Efficient Speech Recognitioncited by 0
  35. 2021Defending Against Adversarial Denial-of-Service Data Poisoning Attackscited by 0
  36. 2022Searching Similarity Measure for Binarized Neural Networkscited by 0
  37. 2022Virtual embeddings and self-consistency for self-supervised learningcited by 0
  38. 2023Verbal behavior without syntactic structures: beyond Skinner and Chomskycited by 0

50 most cited of 63 All 63 (JSON)