HackerPapers

arXiv:1412.5567cs.CL

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

Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, Andrew Y. Ng

Abstract

We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a "phoneme." Key to our approach is a well-optimized RNN training system that uses multiple GPUs, as well as a set of novel data synthesis techniques that allow us to efficiently obtain a large amount of varied data for training. Our system, called Deep Speech, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.0% error on the full test set. Deep Speech also handles challenging noisy environments better than widely used, state-of-the-art commercial speech systems.

arXiv comments
Journal reference
DOI
Subjects
cs.CLComputation and Language cs.LGMachine Learning cs.NENeural and Evolutionary Computing

On Hacker News

Linked by 6 identifiable commenters in 6 comments across 6 threads, from Dec 2014 to Aug 2021. Found in 4 HN submissions from Dec 2014 to Aug 2018. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments6 threads

  1. Mozilla Common Voice Adds 16 New Languages and 4,600 New Hours of Speech 1 comment

    • 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]…

      orraView on HNParent context

  2. A TensorFlow implementation of Baidu's DeepSpeech architecture 1 comment

    • 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…

      kdavisView on HNParent context

  3. How to Train Baidu's Deepspeech Model with Kur 1 comment

    • 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.

      stephensonscoView on HNParent context

  4. How Baidu is improving Mandarin voice recognition with deep learning 1 comment

    • > 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…

      oskaView on HNParent context

  5. What's Wrong with Deep Learning? 1 comment

    • 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…

      jhartmannView on HNParent context

  6. Baidu Research Achieves Speech Recognition Breakthrough with “Deep Speech” 1 comment

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.