Baidu Research Technology

Deep Voice: Real-Time Neural Text-to-Speech for Production

2018-01-17T16:20:53+00:00 February 28th, 2017|

Baidu Research presents Deep Voice, a production-quality text-to-speech system constructed entirely from deep neural networks. The biggest obstacle to building such a system thus far has been the speed of audio synthesis – previous approaches have taken minutes or hours to generate only a few seconds of speech. We solve this challenge and show that [...]

Bringing HPC Techniques to Deep Learning

2018-01-17T16:20:53+00:00 February 21st, 2017|

Summary: Neural networks have grown in scale over the past several years, and training can require a massive amount of data and computational resources. To provide the required amount of compute power, we scale models to dozens of GPUs using a technique common in high-performance computing (HPC) but underused in deep learning. This technique, the [...]

MIT Tech Review Features Baidu’s Deep Speech in Top 10 List of Breakthrough Technologies

2018-01-17T16:20:53+00:00 February 25th, 2016|

MIT Tech Review released its annual Top 10 Breakthrough Technologies list this week, featuring Baidu's Deep Speech in the category of "Conversational Interfaces." Reporter Will Knight writes: "Voice interfaces have been a dream of technologists (not to mention science fiction writers) for many decades. But in recent years, thanks to some impressive advances in machine [...]

SVAIL Tech Notes: *Around the World in 60 Days

2018-01-17T16:20:53+00:00 February 9th, 2016|

  Read the full post here. Ryan Prenger and Tony Han, research scientists at Baidu’s Silicon Valley AI Lab, have posted a Tech Note about how SVAIL enabled the Baidu Deep Speech system to recognize Mandarin in about sixty days, an ambitious project. They write: ...In just a few months, we produced a Mandarin speech [...]

Baidu’s Silicon Valley AI Lab Releases Warp-CTC, Open Source AI Software

2018-01-17T17:25:37+00:00 January 14th, 2016|

Today Baidu's Silicon Valley AI Lab (SVAIL) released Warp-CTC, open source software for the machine learning community. Warp-CTC can be used to solve supervised problems that map an input sequence to an output sequence, such as speech recognition.  Get Warp-CTC and read more here  Warp-CTC Q&A Q. What is Warp-CTC? A. Warp-CTC is an open source implementation [...]

“Deep Speech” From Baidu’s Silicon Valley AI Lab Recognizes Both English and Mandarin With Single Learning Algorithm

2018-01-17T17:25:37+00:00 December 9th, 2015|

At the NIPS conference today in Montreal, SVAIL unveiled new results for Deep Speech. Results include the ability to accurately recognize both English and Mandarin with a single learning algorithm.  The Deep Speech system, which was announced last year, initially focused on improving English speech recognition accuracy in noisy environments (for example, restaurants, cars [...]

SVAIL Tech Notes: Deploying Deep Neural Networks Efficiently

2018-01-17T17:25:37+00:00 November 25th, 2015|

Deep neural networks are increasingly important for powering AI-based applications but deploying them at scale is a challenge. In this video, Christopher Fougner, Research Scientist in Baidu Research's Silicon Valley AI Lab, talks about how we use GPUs to solve this problem. Some key points made by Chris: Deep neural networks are increasingly important for powering [...]

SVAIL’s Bryan Catanzaro on HPC and Deep Learning

2018-01-17T16:20:54+00:00 November 25th, 2015|

Advancements in High Performance Computing are enabling researchers worldwide to make great progress in AI. In this video, Bryan Catanzaro, senior researcher in Baidu Research's Silicon Valley AI Lab, talks about AI projects at Baidu and how the team uses HPC to scale deep learning. Some key points made by Bryan: Progress in AI depends [...]

SVAIL Tech Notes: Optimizing RNN Performance

2018-01-17T16:20:54+00:00 September 30th, 2015|

Erich Elsen, systems researcher at Baidu’s Silicon Valley AI Lab, has written a blog post on “Optimizing RNN Performance.”  This is the first in a series of technical posts by SVAIL researchers and engineers on AI techniques, tips and trends. Erich writes:   “Most researchers engaging in neural network research have been using GPUs for training for [...]

What’s New in Deep Learning – A Talk by Baidu Researchers

2015-11-24T02:01:06+00:00 September 23rd, 2015|

SF Meetup is hosting an event at NVIDIA on October 6th, 2015 on the topic of What’s New in Deep Learning - A Talk by Baidu Researchers. Awni Hannun and Erich Elsen from Baidu Research will share some insights from their groundbreaking work at Baidu Research and its application to complex speech recognition. Awni previously [...]