← All works
Research paper

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

At a glance

Neural networks transcribed English and Mandarin speech, matching human transcription on some benchmarks.

In one paragraph

Extended end-to-end speech recognition to English and Mandarin, learning to transcribe audio with neural networks. Faster training enabled larger experiments, while efficient deployment supported online use. Matched human transcription on some benchmarks. Published at ICML 2016; first released as a preprint in 2015.

Authors 69

  1. Dario Amodei
  2. Sundaram Ananthanarayanan
  3. Rishita Anubhai
  4. Jingliang Bai
  5. Eric Battenberg
  6. Carl Case
  7. Jared Casper
  8. Bryan Catanzaro
  9. Qiang Cheng
  10. Guoliang Chen
  11. Jie Chen
  12. Jingdong Chen
  13. Zhijie Chen
  14. Mike Chrzanowski
  15. Adam Coates
  16. Greg Diamos
  17. Ke Ding
  18. Niandong Du
  19. Erich Elsen
  20. Jesse Engel
  21. Weiwei Fang
  22. Jim Fan
  23. Christopher Fougner
  24. Liang Gao
  25. Caixia Gong
  26. Awni Hannun
  27. Tony Han
  28. Lappi Johannes
  29. Bing Jiang
  30. Cai Ju
  31. Billy Jun
  32. Patrick LeGresley
  33. Libby Lin
  34. Junjie Liu
  35. Yang Liu
  36. Weigao Li
  37. Xiangang Li
  38. Dongpeng Ma
  39. Sharan Narang
  40. Andrew Ng
  41. Sherjil Ozair
  42. Yiping Peng
  43. Ryan Prenger
  44. Sheng Qian
  45. Zongfeng Quan
  46. Jonathan Raiman
  47. Vinay Rao
  48. Sanjeev Satheesh
  49. David Seetapun
  50. Shubho Sengupta
  51. Kavya Srinet
  52. Anuroop Sriram
  53. Haiyuan Tang
  54. Liliang Tang
  55. Chong Wang
  56. Jidong Wang
  57. Kaifu Wang
  58. Yi Wang
  59. Zhijian Wang
  60. Zhiqian Wang
  61. Shuang Wu
  62. Likai Wei
  63. Bo Xiao
  64. Wen Xie
  65. Yan Xie
  66. Dani Yogatama
  67. Bin Yuan
  68. Jun Zhan
  69. Zhenyao Zhu

Organizations

Credited for this work at publication.