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

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by cute_boi

Tue, 07 Jul 2026 19:03:23 GMT

No need stupid moving texts. CS231n: Convolutional Neural Networks for Visual Recognition - https://cs231n.github.io/ The Unreasonable Effectiveness of Recurrent Neural Networks - https://karpathy.github.io/2015/05/21/rnn-effectiveness/ Understanding LSTM Networks - https://colah.github.io/posts/2015-08-Understanding-LSTMs/ ImageNet Classification with Deep Convolutional Neural Networks - https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436... Deep Residual Learning for Image Recognition - https://arxiv.org/abs/1512.03385 Multi-Scale Context Aggregation by Dilated Convolutions…

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by gooob

Tue, 07 Jul 2026 18:54:32 GMT

https://colah.github.io/posts/2015-08-Understanding-LSTMs/ https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436... https://papers.nips.cc/paper_files/paper/2012/file/c399862d3... https://arxiv.org/pdf/1512.03385 https://arxiv.org/pdf/1511.07122 https://arxiv.org/pdf/1603.05027 https://arxiv.org/pdf/1409.2329 https://arxiv.org/pdf/1512.02595 https://arxiv.org/pdf/1409.0473 https://arxiv.org/pdf/1506.03134 https://arxiv.org/pdf/1706.03762 https://nlp.seas.harvard.edu/annotated-transformer/ https://arxiv.org/pdf/1410.5401 https://arxiv.org/pdf/1706.01427 https://arxiv.org/pdf/1806.01822…

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by brandonb

Mon, 15 Dec 2025 16:50:01 GMT

The acoustic model of a speech recognizer used to be a GMM, which mapped a pre-processed acoustic signal vector (generally MFCCs-Mel-Frequency Cepstral Coefficients) to an HMM state. Now those layers are neural nets, so acoustic pre-processing, GMM, and HMM are all subsumed by the neural network and trained end-to-end. One early piece of work here was DeepSpeech2 (2015): https://arxiv.org/pdf/1512.02595

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by is_true

Sat, 18 May 2024 12:26:29 GMT

a backup just in case https://nlp.seas.harvard.edu/annotated-transformer/ https://scottaaronson.blog/?p=762 https://karpathy.github.io/2015/05/21/rnn-effectiveness/ https://colah.github.io/posts/2015-08-Understanding-LSTMs/ https://arxiv.org/pdf/1409.2329.pdf https://www.cs.toronto.edu/~hinton/absps/colt93.pdf https://arxiv.org/pdf/1506.03134.pdf https://proceedings.neurips.cc/paper_files/paper/2012/file/c... https://arxiv.org/pdf/1511.06391.pdf https://arxiv.org/pdf/1811.06965.pdf https://arxiv.org/pdf/1512.03385.pdf https://arxiv.org/pdf/1511.07122.pdf https://arxiv.org/pdf/1704.01212.pdf…

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by rahimnathwani

Thu, 10 Aug 2023 11:44:20 GMT

Yes it is. Tangent: Anthropic's CEO worked on Mandarin speech recognition at Baidu: https://arxiv.org/abs/1512.02595

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by koningrobot

Tue, 23 May 2023 15:00:58 GMT

Have you seen the author list of DeepSpeech2? https://arxiv.org/abs/1512.02595

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by est31

Fri, 27 Dec 2019 01:31:24 GMT

> M-AILABS data contains 9 language varieties with a modified BSD 3-Clause License, however there is no community-driven aspect. There is certainly an aspect, as M-AILABS sources their data mainly from the librivox project, which is community-driven. To give ballpark numbers on what it would have cost if you had had to pay people for providing the data instead of getting it for free: It's low skilled labour so you'll likely find people to do it slightly above minimum wage. Let's take Germany as I'm most familiar with its rules and because that's where Common Voice is headquartered. Minimum…

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by gok

Thu, 05 Dec 2019 15:52:22 GMT

But these results are about in line with other CTC systems. The original Baidu paper [1] had 7.89% with original Deep Speech and 5.33% with "Deep Speech 2" where they threw more complicated networks at it and added another 11K hours of external speech traingin data. [1] https://arxiv.org/pdf/1512.02595v1.pdf

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by TD-Linux

Wed, 29 Nov 2017 22:17:04 GMT

In the Baidu Deep Speech 2 paper, the Baidu implementation is able to get 5.33%, and a human 5.83%. https://arxiv.org/pdf/1512.02595v1.pdf

Paper and discussion history. A mention is not an endorsement.

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin — mentioned by skoocda

Wed, 06 Jul 2016 23:52:55 GMT

* I should clarify as well, for your first question. State of the art is generally either IBM's 2016 English Conversational Telephone Speech Recognition System [0], or Baidu's DeepSpeech2 [1]. IBM's is a little more complex, but I'd actually argue Baidu is more promising due to the robust ability to learn new languages. 0: arxiv.org/abs/1604.08242 1: arxiv.org/abs/1512.02595

Paper and discussion history. A mention is not an endorsement.

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

Wed, 09 Dec 2015 23:12:28 GMT

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

105 points; 19 discussion replies on HN. Paper and source history. A submission is not an endorsement.