Collaborating Authors

How to use Watson Speech to Text utilities to increase accuracy - Watson


June 23, 2017 Written by: Simon O'Doherty Key Points: โ€“ Learn how to use Watson Speech to Text utilities to increase your accuracy โ€“ We've included links so you can download S2T utilities โ€“ Sample .wav I thought I would take a moment to play with Watson Speech to Text and a utility that was released a few months ago. The Speech to Text Utils allows you to train S2T using your existing conversational system. To give a quick demo, I got my son to ask about buying a puppy. Of course the recording is crystal clear, which is why such a good result.

Michael Keaton deserves an award for the Batman comment he made at a graduation speech


Michael Keaton was a damn good Batman. SEE ALSO: Holy prequel, Batman! The legendary actor gave a commencement speech at Kent State University graduation recently, and he wrapped things up in the most unbelievably wonderful way. Michael Keaton closed his commencement speech at Kent State with "I'm Batman." And this is why Michael Keaton is the best.

Speech Research Lab: Speech Synthesis, Speech Recognition, and Speech Processing

AITopics Original Links

The ModelTalker TTS system converts plain English text to speech. It uses a text to phoneme system which includes capabilities for parsing ToBI-like descriptions of the intonation. Synthesis is accomplished through a combination of database-driven speech and a variant on diphone-based phoneme to sound engines known as Biphone-Constrained Concatenation (BCC). Speech stored in the database encompasses common words and phrases in different contexts as well as a complete set of biphones. The BCC sound engine results in smoother, more natural speech, without sacrificing the ability to quickly "capture" new voices in the biphone inventories for the system.

Mozilla Deep Speech: An open source Speech-to-Text Engine


Open source Speech recognition Engine based on Tensor-flow. Deep-Speech is a source engine which is easily used by any individual as a Speech-To-Text (STT) engine; use to display the prepared machine learning strategies. Project Deep-Speech applies Google's Tensor Flow to generate better performance with fewer challenges. It is an engine that points to produce discourse recognition innovation and prepared models openly and accessible to engineers and it is additionally a profound learning-based Automatic Speech Recognition Engine (ASR) with a straightforward API. They moreover give pre-trained English models.

To Curb Fake News and Hate, We Need a Little Less Speech


Social media are doomsday machines. They distract, divide, and madden; we can no longer hear each other, speak coherently, or even think. As a result, our social, civic, and political ligands are dissolving. Everywhere, people consult their screens to affirm what they already think and repeat what like-minded people have already said. They submit to surveillance and welcome algorithmic manipulation.