×
Speech Recognition

Where Does AI Stand Today?

In this blog, Jin Rong, VP of Research at Alibaba DAMO Academy, discusses the current practices, innovations, and future avenues of exploration in AI.

Building Smarter Apps - Learn How to Integrate AI

This article discusses AI and how to integrate AI with business applications for better outcomes. It also briefs about Alibaba Cloud's image search service.

Improving Content Moderation with Artificial Intelligence

Reviewing live video content is a resource intensive and complex job. We will explore how AI-based solutions such as Alibaba Cloud’s ApsaraVideo Live can make a difference.

Alibaba Cloud DFSMN Breaks the Barriers of Speech Recognition Accuracy with MaxCompute

Alibaba Cloud makes its high-accuracy speech recognition model (96.04%), Deep Feedforward Sequential Memory Network (DFSMN), open source on GitHub.

Alibaba Discloses Future Plans for IoT and Intelligent Voice Systems

Yan Zhijie, Senior Staff Algorithm Engineer of Alibaba Group recently delivered a keynote speech around the developments of AI, IoT, and voice-based intelligent systems at the AITech2018 Conference.

Interview with Dr. Yu Kai of AISpeech – The Importance of Naturalness in Natural Language Processing

Dr. Yu Kai of AISpeech discusses how the advances in the natural language processing (NLP) have improved human-machine interactions and how the technology will evolve in the coming years.

Breaking the Communication Barriers with Natural Language Processing (NLP)

With advancements in artificial intelligence, human-computer interactions are becoming increasingly pervasive.

Interspeech 2017 Far-field Speech Recognition Technology

Far-field speech recognition is an essential technology for speech interactions, aims to enable smart devices to recognize distant human speech.

Interspeech 2017 Small-Footprint Keyword Spotting Technology

In this article, we will take a look at the basic technical architecture of keyword spotting technology, along with the newest research results given ...

Interspeech 2017 Speech Synthesis Technology

Participants from renowned research institutes, universities, and companies have shared their newest technologies and products during Interspeech 2017.

Interspeech 2017 Series Acoustic Model for Speech Recognition Technology

Research in ASR (Automatic Speech Recognition) aims to enable computers to "understand" human speech and convert it into text.