Poynter: With Amazon Polly experiment, The Washington Post hopes to capitalize on growing interest in audio

Poynter: With Amazon Polly experiment, The Washington Post hopes to capitalize on growing interest in audio. “The last Washington Post column I came across was only interesting because a computer read it to me. Amazon Polly is a text-to-speech service that sounds like a cross between a customer service agent and Siri. Its ‘lifelike’ reading is dispassionate, and each comma prompts an overly long pause between words. Yet, I found myself listening to several articles for at least a few minutes apiece as I stared into empty space at work. And that’s exactly what The Post is shooting for.”

Please Help Pete Warden Train His Robot With Open Speech Data

Hey! Pete Warden is trying to train his robot and needs some help – specifically he needs a data set of spoken words. Can you help? “I’ve put together a website … that asks you to speak about 100 words into the microphone, records the results, and then lets you submit the clips. I’m then hoping to release an open source data set out of these contributions, along with a TensorFlow example of a simple spoken word recognizer. The website itself is a little Flask app running on GCE, and the source code is up on github. I know it doesn’t work on iOS unfortunately, but it should work on Android devices, and any desktop machine with a microphone.”

Philadelphia Inquirer: ‘Fresh Air,’ fresh forever: 30 years as national show, new digital archive

Philadelphia Inquirer: ‘Fresh Air,’ fresh forever: 30 years as national show, new digital archive. “Fresh Air has been digitized, archived, and put online. As many of the old, old, tapes as possible, going back to the 1970s, have been baked (that’s what you do!), played, and their data turned into WAV and mp3 files and parked at a big catalogue site named WorldCat.org… More than 8,000 segments across more than 7,000 shows are now online.” If this is ringing a bell for you, I mentioned the grant for this project back in 2015.

NPR: Videotapes Are Becoming Unwatchable As Archivists Work To Save Them

NPR: Videotapes Are Becoming Unwatchable As Archivists Work To Save Them. “[Mary] Kidd and the others are archivists and preservationists, and they’re part of a group called XFR Collective (pronounced Transfer Collective). Most work professionally, but they volunteer their free time to do this. And while the mood is light, there is a sense of a deadline…. That’s because research suggests that tapes like this aren’t going to live beyond 15 to 20 years. Some call this the ‘magnetic media crisis,’ and archivists, preservationists, and librarians like the ones in the XFR Collective are trying to reverse it.”

Internet Archive: Dreaming of Semantic Audio Restoration at a Massive Scale

The Internet Archive: Dreaming of Semantic Audio Restoration at a Massive Scale. “The Great 78 Project will collect and digitize over 400,000 digitized 78rpm recordings to make them publicly available, creating a rich data set to do large scale analysis. These transfers are being done with four different styli shapes and sizes at the same time, and all recorded at 96KHz/24bit lossless samples, and in stereo (even though the records are in mono, this provides more information about the contours of the groove). This means each groove has 8 different high-resolution representations of every 11 microns. Furthermore, there are often multiple copies of the same recording that would have been stamped and used differently. So, modeling the wear on the record and using that to reconstruct what would have been on the master may be possible.”

Naked Security: Chrome bug that lets sites secretly record you ‘not a flaw’, insists Google

Naked Security: Chrome bug that lets sites secretly record you ‘not a flaw’, insists Google. “Remember last year’s Google Chrome bug that gave pirates a way to steal streaming movies? Well, we’re ready for our closeup, Mr DeMille! This time, we’re potentially the stars of hackers’ movies: there’s a Google Chrome ‘bug’ (depending on who you ask) that allows sites to surreptitiously record audio and visual, all without an indicator light.”

BusinessWire: Podcast Discovery Made Easy with PodSearch (PRESS RELEASE)

There’s a new podcast directory in town (PRESS RELEASE). “PodSearch, available free to listeners through a website and mobile app, is designed to help everyone discover podcasts that reflect their personal interests and keep them in-the-know about new podcasts as they are released. PodSearch goes beyond the typical top show lists, with unique and easy-to-use search features like keyword search, detailed categories, new shows, links to many different listening apps, links to tour dates where the host or show is appearing and can even generate personalized podcast recommendations based on the user’s interests.” I have yet to find a podcast search engine I like – might be time for another try.

UPDATE: Never mind. I just went to the site and you can’t even do a search without signing up for an account. Ick. No thank you.