Presented By O’Reilly and Intel AI
Put AI to work
April 10-11, 2018: Training
April 11-13, 2018: Tutorials & Conference
Beijing, CN

Deep learning for speech recognition and profiling

This will be presented in English.

Yishay Carmiel (IntelligentWire)
14:5015:30 Thursday, April 12, 2018
实施人工智能 (Implementing AI), 英文讲话 (Presented in English)
Location: 多功能厅2(Function Room 2) Level: Beginner
Secondary topics:  自然语言与语音技术(Natural Language and Speech Technologies)

必要预备知识 (Prerequisite Knowledge)

基本理解机器学习
A basic understanding of machine learning

您将学到什么 (What you'll learn)

了解如何将深度学习应用于基于语音的应用程序以及还有的挑战
Learn how deep learning is being applied to speech-based applications and the remaining challenges

描述 (Description)

本讲话将用英语授课,同时会提供中文同声传译。中文版本摘要会在英文摘要下面给出。

For years, humans have dreamed of systems that truly understand humans speaking (in different environments, with a variety of accents and languages)—with no success. Pinpointing effective strategies for creating such a system seemed impossible.

In the past years, breakthroughs in AI and especially in deep learning have changed everything in the quest for speech recognition. Applying deep learning techniques has enabled remarkable results. Today, we see this leap forward in development manifesting in a wide range of products.

Yishay Carmiel offers an overview of neural models in speech applications, covering the dominant techniques and the elements that have contributed to the rapid progress. Yishay also looks to the future, examining which problems still remain and how far we are from solving them.

Topics include:

  • How neural models are being applied for speech recognition, especially for acoustic and language models
  • Speech profiling, its main applications, and how neural models are applied
  • Future challenges and research in a speech-based application and how neural models will be part of it

语音识别的梦想是一个能在不同的环境下、能应对多种口音和语言的、真正理解人类语言的系统。几十年来对这个问题的尝试都没有成功。寻找一个能有效地创建这样的系统的策略看起来是不可能完成的任务。

然而,在过去的几年间人工智能和深度学习领域的突破已经颠覆了对语音识别探索的一切。深度学习技术在语音识别领域的运用已经取得了显著的进步。现在我们已经在非常多样的产品里面看到了展示出来的发展的跃升。本议题将回顾一下神经网络模型是如何被应用于基于语音的应用,检视带来这些快速进步的因素,并会讨论一下未来的发展以及我们离完全解决这个问题还有多远。

本议题将会回顾如下一些内容:
• 神经网络模型是如何被持续地应用于语音识别,特别是语音和语言的模型。
• 什么是语音画像、它的主要应用和如何应用神经网络模型。
• 未来基于语音应用的研究和挑战,以及神经网络模型在其中处于什么地位。

Photo of Yishay Carmiel

Yishay Carmiel

IntelligentWire

Yishay Carmiel is the founder of IntelligentWire, a company that develops and implements industry-leading deep learning and AI technologies for automatic speech recognition (ASR), natural language processing (NLP), and advanced voice data extraction, and the head of Spoken Labs, the strategic artificial intelligence and machine learning research arm of Spoken Communications. Yishay and his teams are currently working on bleeding-edge innovations that make the real-time customer experience a reality—at scale. Yishay has nearly 20 years’ experience as an algorithm scientist and technology leader building large-scale machine learning algorithms and serving as a deep learning expert.