Semi-supervised learning
0
New speech recognition experiments demonstrate how machine learning can scale
0

Customer interactions with Alexa are constantly growing more complex, and on the Alexa science team, we strive to stay ahead of the curve by continuously ...

0
Two new papers discuss how Alexa recognizes sounds
0

Last year, Amazon announced the beta release of Alexa Guard, a new service that lets customers who are leaving the house instruct their Echo devices to ...

0
The 16 Alexa-related papers at this year’s Interspeech
0

At next week’s Interspeech, the largest conference on the science and technology of spoken-language processing, Alexa researchers have 16 papers, which span ...

0
Alexa at five: Looking back, looking forward
0

Today is the fifth anniversary of the launch of the Amazon Echo, so in a talk I gave yesterday at the Web Summit in Lisbon, I looked at how far Alexa has ...

0
The science behind an Amazon Echo feature that helped save a puppy
0

Jonathan and Kathy, an Orlando-based couple, were out visiting a neighbor a few days before Christmas 2020 when Jonathan got an unusual alert from their ...

0
Improving unsupervised sentence-pair comparison
0

Many tasks in natural-language processing and information retrieval involve pairwise comparisons of sentences — for example, sentence similarity detection, ...

0
Ankan Bansal’s long journey into the world of computer vision
0

Think back to what you were doing the summer after your freshman year in college — for many of us, that likely didn’t include working on a project that ...

0
Bringing the power of deep learning to data in tables
0

In recent years, deep neural networks have been responsible for most top-performing AI systems. In particular, natural-language processing (NLP) ...

0
Making machine translation more robust, consistent, and stable
0

Like many other machine learning applications, neural machine translation (NMT) benefits from overparameterized deep neural models — models so large that ...

0
More-inclusive speech recognition with cross-utterance rescoring
0

Automatic-speech-recognition (ASR) models, which convert speech to text in voice agents, typically have two stages. The first stage involves a deep neural ...

Rockstary Reviews
Logo
Shopping cart