Deep Speech: Scaling up end-to-end speech recognition · HackerPapers discussions

Deep Speech: Scaling up end-to-end speech recognition — mentioned by orra

Thu, 05 Aug 2021 14:13:45 GMT

Mozilla announced Deep Speech[1] around the same time as Common Voice. Mozilla Deep Speech is an open source speech recognition engine, based upon Baidu's Deep Speech research paper[2]. Unsurprisingly, Deep Speech requires a corpus such as... Common Voice. [1] https://github.com/mozilla/DeepSpeech [2] https://arxiv.org/abs/1412.5567

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

Deep Speech: Scaling up end-to-end speech recognition — HN submission

Tue, 07 Aug 2018 23:00:33 GMT

Deep Speech: Scaling up end-to-end speech recognition (2014)

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Speech: Scaling up end-to-end speech recognition — mentioned by kdavis

Sun, 03 Dec 2017 23:27:27 GMT

Added an enhancement request, issue 1064[1], to github, asking for the clients to support longer audio clips. I can't promise when we'll get to it, as from now until new year is a bit of a wash. I don't know of any detailed comparisons of commercial solutions. However, with respect to pure word error rate, the article[2] does a comparison of several engines as of circa 2015. [1] https://github.com/mozilla/DeepSpeech/issues/1064 [2] https://arxiv.org/abs/1412.5567

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

Deep Speech: Scaling up end-to-end speech recognition — mentioned by stephensonsco

Mon, 20 Feb 2017 19:26:46 GMT

Deepgram just posted an open sourced Kur Speech Recognition example based on Deepspeech (https://arxiv.org/abs/1412.5567) on our blog. We'd love to help people get it running and spread the DNN speech love.

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

Deep Speech: Scaling up end-to-end speech recognition — mentioned by oska

Fri, 09 Oct 2015 07:54:55 GMT

> Of course, OCR and speech recognition are somewhat different fields, but if anyone is an expert for Chinese language, then it should be Baidu. It's not about being experts in Mandarin. The basis of their approach is that it doesn't encompass any expert design. It's an end-to-end deep learning approach. From the article: > Our system is different than that system in that it’s more what we call end-to-end. Rather than having a lot of human-engineered components that have been developed over decades of speech research — by looking at the system and saying what features are important or which…

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

Deep Speech: Scaling up end-to-end speech recognition — mentioned by jhartmann

Sun, 14 Jun 2015 14:39:47 GMT

Actually, state of the art speech recognition has switched over to having a Recursive Neural Network directly run over the audio input. Take a look at the paper at http://arxiv.org/abs/1412.5567 and http://usa.baidu.com/deep-speech-lessons-from-deep-learning/ However combining learning features with other systems is a very powerful approach and combining SVM's on top of the learned features of a Neural Network I would say is common. I personally am more interested in approaches like Deep Fried Convnets (http://arxiv.org/abs/1412.7149) that combine kernel methods as part of the Neural Networks…

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

Deep Speech: Scaling up end-to-end speech recognition — HN submission

Sat, 14 Feb 2015 13:30:34 GMT

Deep Speech: Scaling up end-to-end speech recognition

63 points; 8 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Speech: Scaling up end-to-end speech recognition — HN submission

Fri, 19 Dec 2014 00:03:47 GMT

DeepSpeech: Scaling up end-to-end speech recognition [pdf]

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Deep Speech: Scaling up end-to-end speech recognition — mentioned by redknight666

Thu, 18 Dec 2014 22:23:56 GMT

The actual paper: http://arxiv.org/abs/1412.5567

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

Deep Speech: Scaling up end-to-end speech recognition — HN submission

Thu, 18 Dec 2014 19:14:04 GMT

DeepSpeech: Scaling up end-to-end speech recognition

79 points; 22 discussion replies on HN. Paper and source history. A submission is not an endorsement.