mlsanityData to 14 Oct 2026

The Microsoft 2017 Conversational Speech Recognition System

arXiv 1708.06073 ↗First posted 21 Aug 2017cs.CLcited by 52

Not on the map. Why?

Abstract (arXiv)

We describe the 2017 version of Microsoft's conversational speech recognition system, in which we update our 2016 system with recent developments in neural-network-based acoustic and language modeling to further advance the state of the art on the Switchboard speech recognition task. The system adds a CNN-BLSTM acoustic model to the set of model architectures we combined previously, and includes character-based and dialog session aware LSTM language models in rescoring. For system combination we adopt a two-stage approach, whereby subsets of acoustic models are first combined at the senone/frame level, followed by a word-level voting via confusion networks. We also added a confusion network rescoring step after system combination. The resulting system yields a 5.1% word error rate on the 2000 Switchboard evaluation set.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 11; 2023: 8; 2024: 5; 2025: 2; 2026: 1.

52 papers.

Sort:

By area:

  1. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  2. 2021Dive into Deep Learningcited by 111
  3. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  4. 2021On the limit of English conversational speech recognitioncited by 30
  5. 2022Investigation of Data Augmentation Techniques for Disordered Speech Recognitioncited by 27
  6. 2021Neural Delay Differential Equationscited by 26
  7. 2022FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classificationcited by 26
  8. 2021Look Who's Talking: Active Speaker Detection in the Wildcited by 21
  9. 2022Audio-driven Neural Gesture Reenactment with Video Motion Graphscited by 18
  10. 2022Recent Progress in the CUHK Dysarthric Speech Recognition Systemcited by 17
  11. 2021Transformer Language Models with LSTM-based Cross-utterance Information Representationcited by 15
  12. 2024Measuring the Accuracy of Automatic Speech Recognition Solutionscited by 15
38 more
  1. 2021Adapting Long Context NLM for ASR Rescoring in Conversational Agentscited by 12
  2. 2021Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognitioncited by 10
  3. 2023Assessing SATNet's Ability to Solve the Symbol Grounding Problemcited by 10
  4. 2021Platform for Situated Intelligencecited by 9
  5. 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Modelscited by 9
  6. 2021On Architectures and Training for Raw Waveform Feature Extraction in ASRcited by 8
  7. 2021ASR Adaptation for E-commerce Chatbots using Cross-Utterance Context and Multi-Task Language Modelingcited by 7
  8. 2022Language technology practitioners as language managers: arbitrating data bias and predictive bias in ASRcited by 7
  9. 2023Modular Domain Adaptation for Conformer-Based Streaming ASRcited by 7
  10. 2021Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognitioncited by 6
  11. 2021ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guaranteescited by 6
  12. 2022Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classificationcited by 6
  13. 2022LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videoscited by 6
  14. 2023Personalized Predictive ASR for Latency Reduction in Voice Assistantscited by 6
  15. 2023SAPIEN: Affective Virtual Agents Powered by Large Language Modelscited by 6
  16. 2022Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Datacited by 5
  17. 2022MyMove: Facilitating Older Adults to Collect In-Situ Activity Labels on a Smartwatch with Speechcited by 5
  18. 2021Large-Scale News Classification using BERT Language Model: Spark NLP Approachcited by 3
  19. 2021Evaluating Models of Robust Word Recognition with Serial Reproductioncited by 2
  20. 2021Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Modelcited by 2
  21. 2021A Benchmarking on Cloud based Speech-To-Text Services for French Speech and Background Noise Effectcited by 2
  22. 2021Multi-Scale Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 2
  23. 2023Using Kaldi for Automatic Speech Recognition of Conversational Austrian Germancited by 2
  24. 2021Speech Pattern based Black-box Model Watermarking for Automatic Speech Recognitioncited by 1
  25. 2023Leveraging Cross-Utterance Context For ASR Decodingcited by 1
  26. 2024Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methodscited by 1
  27. 2024Acoustic Model Optimization over Multiple Data Sources: Merging and Valuationcited by 1
  28. 2025xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloadscited by 1
  29. 2021Practical Speech Re-use Prevention in Voice-driven Servicescited by 0
  30. 2021"Weak AI" is Likely to Never Become "Strong AI", So What is its Greatest Value for us?cited by 0
  31. 2021Drivers' Manoeuvre Modelling and Prediction for Safe HRIcited by 0
  32. 2021Graphs as Tools to Improve Deep Learning Methodscited by 0
  33. 2021On the Application of Data-Driven Deep Neural Networks in Linear and Nonlinear Structural Dynamicscited by 0
  34. 2021Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognitioncited by 0
  35. 2022Unified Simulation, Perception, and Generation of Human Behaviorcited by 0
  36. 2023Neural Delay Differential Equations: System Reconstruction and Image Classificationcited by 0
  37. 2023Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Modelscited by 0
  38. 2024Child Speech Recognition in Human-Robot Interaction: Problem Solved?cited by 0

50 most cited of 52 All 52 (JSON)