Employee Advocacy At Scale with Hootsuite Amplify

  Ciaran talks to Alistair Beech from the University of Manchester and explores how they are using Hootsuite’s Amplify App to engage senior staff advocates to help spread the word on the University’s amazing research and campaign initiatives. Based at the largest single-site university in the UK, Alistair shares with us how his communications team went about persuading influential members of the University’s community to engage with their advocacy programme. How do you go about convincing busy staff members and academics that helping you to share great content about your organisation is a beneficial activity for them to invest their time into? If you are looking at any employee social engagement at scale, Alistair has some great pointers and key learnings that will help you to build a useful and engaging internal advocacy programme. Listen in and learn how to engage at scale. Useful Links Hootsuite Amplify https://hootsuite.com/en-gb/products/amplify >Hootsuite https://hootsuite.com/en-gb/ The University of Manchester https://www.manchester.ac.uk/connect/social-media/  Alistair Beech   https://twitter.com/alistairbeech https://www.linkedin.com/in/alistairbeech/ James Baker https://twitter.com/jameshbaker1

Share
Old Bulgarian Lottery Tickets Were Winning at Design

I couldn’t find much information about these lottery tickets from communist Bulgaria, but the design alone makes it worth sharing here. Heavily inspired by Russian constructivism, these tickets are an amazing display of great layouts produced with abstract shapes only. Images via Delcampe.net.


Thanks for being a subscriber, here is your FREE house vector icons set.

Share
Website Design in Naples Florida for Jeff Wilson Pool Services

We recently launched a redesigned website for Jeff Wilson Pool Service in Naples, Florida to continue to expand on their growth and success in the Southwest Florida market.

With over 60 employees, and serving Naples Florida since 1985, Jeff Wilson Pool Service is the premier pool service, maintenance and renovation company in the area.

We’ve been working with JWPS since 2009, and together we’ve built a powerful online presence that attracts new customers every day through Google searches for Pool Cleaning in Naples Florida and a variety of other search terms.

Today, the new website engages visitors with stunning visuals and important information about their experience and services.

Each page of the site is carefully organized and helps visitors find the information quickly and easily. Potential customers can schedule a consultation for a renovation, decide on a service plan that fits their needs, and much more.

Check out the new Jeff Wilson Pool Service!

Are you in Naples, Florida and need a successful website for your business or organization?
Let’s talk!

Share
The Magic of Mobile | Social Media Help Desk Episode 76

The future is mobile. You might even be reading this on your phone right now! The truth is that adults spend nearly three hours of their day on their phone, and that’s just the average. If your website isn’t mobile-friendly, your site could be underperforming when it comes to the user experience. This week on the Social Media Help Desk, I’m sitting down with our host Alexandra Hall and guest Layla Lamajier as we discuss tips for making some mobile site magic, the week’s trending topics, and providing you with the tips you need to stand out on IG.

 

Instagram Cuts the Dead Weight (00:00-07:18)

 

We’re kicking the discussion off with news from Instagram as they move toward restricting dangerous weight-loss claims in content. This change comes after years of product pushing from celebrities like the Kardashians who claim products like a weight-loss shake have transformed their bodies. Then we’re getting into the spooky spriting with the dos and don’ts of Halloween marketing on Twitter, and we’re talking about a small addition to Pinterest’s capabilities. 

 

Shine Bright Like an Instagram Diamond in the Rough (07:18-15:14)

 

When 95 million photos and videos are shared on Instagram a day, how do you stand out and get noticed? I’m sharing my 3 tips for better content, lighting, and quality of photos.  I also share how these elements can elevate your Instagram posts. 

 

Be Mobile Minded (15:14-26:09)

 

Layla is wrapping up the day’s discussion with the key factors that make a website “mobile-friendly.” These quick fixes can update your site’s mobile design, functionality, and usability so you can convert more customers and improve the user’s experience online. 

 

Up to 70% of web traffic happens on a mobile device. 

Still not sure if you’re making the most out of mobile? 

CLICK HERE to sign up for a complimentary 30 Minute Website Audit.

 

 

 

Share
Rental Makes Economic Sense: Understanding Aspects of Rental Industry

The first thing that comes in the mind of an entrepreneur when thinking of the rental industry is Airbnb and Uber. Online rental businesses are expanding at a rapid pace making these, one of the most profitable models in the industry.

Early adopters believed the rental Industry to be a passing fad or might turn out to be a disruptive industry that will destroy the profits of all other industries.

The Rental Industry has gathered a venture capital of approx $24 billion since 2010

Over the years, rental industry giants have been receiving generous capital from investors. One of the major factors resulting in the growth of the sharing economy is the target audience in the US, which according to NITA Data, is the wealthiest, full of well-educated people.

The rental industry is rapidly growing as a platform that provides temporary access to various assets. This industry which was valued at $19 billion in 2017 is expected to be $59.4 billion by 2022.

In the US, where the rental industry has been expanding at annual rates of between 5-7% for the past few years and is forecast to stay at the 5% level for the coming few years. The number of adults (in the U.S) using the increasingly popular renting economy is 73.7 million in 2019 and is likely to increase to 86.5 million by 2021.

While rental is an industry in itself, it also accommodates other industries under its umbrella. Many new business models have come up in this industry, one of which is “collaborative consumption”. Where users are consuming a particular commodity together, like in shared workspace. To simplify it further let me share an example with you.

Example:

While websites like rentmojo also exist where a user can go and rent items according to their needs. There are many businesses that have created a new niche within already existing industries. Transportation & logistics segment has successfully adopted the rental model with its already existing business models.

Below are some of the online niche-based ideas, which an entrepreneur can consider while opening a business in the rental industry:

Rental Industry Niche Business Ideas

The Online Rental Industry Report 2019 – 2023

Entrepreneurs with a keen interest in this industry must gain more knowledge before starting a new venture. To enable entrepreneurs make an informed decision, we would like to share information about the recent launch of online rental industry report.

Why should I download Online Rental Industry Report?

The report contains information on different topics that are important for decision making. Here are some points from the report:

  • Growth of the rental industry
  • Opportunities in the rental Industry
  • Challenges faced by entrepreneurs in the rental industry
  • Online niche-based rental business ideas
  • What’s next in the rental industry

Rental Industry Report

Share
Find the Right Keywords Tools You Need for More Search Traffic

If you want to get the job done right, you need the right tools. For example, if you want to grow your search traffic you need the right free keyword research tools. Otherwise, you will struggle to rank your site for high-converting keywords that drive customers and traffic to your site. This topic is so […]

The post 7 Keyword Research Tools You Need for More Search Traffic appeared first on Digital Marketing Strategy.

Share
New Research Questions Asian Brands’ Omnichannel Readiness

It’s no secret that Southeast Asia has a strong preference for mobile devices and digital services – and with projections that the mobile audience across the region will increase by 300% by 2025, companies are working to become digitally ready in theory as well as practice.

As such, omnichannel marketing has become a major focal point for businesses in the region. There’s no denying the strategy’s appeal: it gives customers more choice over their experiences and grants brands access to personalised customer history and data instantly, providing for a universally seamless experience.

To gain a deeper understanding of how companies across Southeast Asia regard and leverage omnichannel marketing, Resulticks commissioned Econsultancy to conduct a survey on how prepared enterprise businesses in the region really are to implement omnichannel strategies.

According to the findings included in the report, ‘The Omnichannel Imperative,’ businesses throughout Southeast Asia are confident in their omnichannel marketing capabilities. Indeed, nearly 70 percent of enterprise companies surveyed believe they have achieved a level of proficiency with omnichannel approaches, with Malaysia and Thailand leading in confidence levels, and fewer than 20 percent disagreeing that they are proficient.

Though the survey provides a sunny outlook for omnichannel readiness in the region, it does not mean all businesses rate themselves equally capable, or that adopting omnichannel strategies is without complications. As omnichannel success is built on a holistic approach to customer engagement, data, technology, and processes must work in harmony to achieve the desired outcomes. This is where many companies – no matter how ready they may think they are to implement omnichannel strategies – begin to face challenges.

Often, these challenges arise because delivering a highly individualised level of customer experience requires companies to consolidate and integrate large amounts of disparate customer data into a single, unified view of the customer. Many businesses find this a major obstacle.

Indeed, the survey revealed the most commonly cited barriers to more effective omnichannel marketing included having too much data to manage, poor data integration, incomplete data and the inability to act on data. More than one in three of the respondents cited such obstacles. Tellingly, the most daunting obstacle was technology and software limitations, with 40 percent of respondents saying technical deficiencies are a key challenge.

Digging deeper into this tech challenge, the survey showed that many business in Southeast Asia are specifically frustrated with the omnichannel software platforms they use. The frustration seemingly concerns vendors inability to satisfactorily enable real-time, personalised campaigns across multiple channels – a necessity for omnichannel customer engagement. Nearly 60 percent of businesses said their needs in enabling multichannel campaign orchestration are not being fulfilled.

Though confidence in implementing omnichannel strategies appears relatively high across the region, many businesses still face significant challenges ranging from prioritising marketing strategies to consolidating data to investing in the right technology to delivering on the omnichannel promise. With the latest findings, businesses across Southeast Asia will not only have a view of some omnichannel learnings that can help preempt some challenges, but also a potential mid-to-long-term roadmap charting their own omnichannel journeys.

The post New Research Questions Asian Brands’ Omnichannel Readiness appeared first on Digital Media Marketing News.

Share
The Definitive Website Accessibility Checklist

Your website can reach a massive audience. Reaching, as well as attracting those users, however, requires a site that anyone can access. That’s why development and marketing teams need to review website accessibility checklists and ensure your site meets web content accessibility guidelines (WCAG).

Keep reading to view our definitive website compliance checklist of 50-plus standards to meet.

WCAG 2.0 checklist

Assess your WCAG compliance fast with our up-to-date WCAG 2.0 checklist:

  • Level A: Make your site accessible to some users.
  • Level AA: Make your site accessible to almost all users.
  • Level AAA: Make your site accessible to all users.

Level A website accessibility checklist

If your company doesn’t have a significant amount of time to dedicate to WCAG compliance, Level A can get you started. With Level A, you make some basic changes to your site that make it accessible to some (but not all) users.

.static-table-heading { color:#fff; font-size:18px; padding: 15px 7px !important; background: #466db2; } .first { line-height: 1.5em; padding:8px; background: #f2f2f2; border: 1px solid #222222 } .second{ line-height: 1.5em; padding:8px; border: 1px solid #222222 }
Level A Web Accessibility Checklist
GuidelineAction Items
Non-text contentAdd alt text to images.

Add alt text to audio and video.

Add names to controls, like “Submit.”

Audio-only and video-onlyWrite transcripts for audio- and video-only content.

Link or place transcripts near audio or video content.

Record audio tracks for video-only media.

CaptionsAdd captions to all videos with sound.
Audio description or media alternativeWrite video transcripts.

Provide audio descriptions of video.

Information and relationshipsUse valid and proper HTML.

Apply clear labels to forms.

Divide content with subheadings.

Meaningful sequenceSeparate navigation menus from content.

Use valid HTML.

Use headings and lists.

Arrange paragraphs in order.

Sensory characteristicsProvide more than one sense, like sight and sound, for instructions.
Color usageAvoid color references in text, like instructing users to click a green button.
Audio controlAllow users to choose when to play audio, versus playing it automatically.
KeyboardRemove any function that uses timed keystrokes, like a double tap.
No keyboard tapEnable navigation control with arrow or “Tab” key.

Eliminate any instances where users cannot navigate or access your site without a keyboard.

Timing adjustableLet users turn off, adjust, or extend any time limits except for real-time events, like an auction.

Allow users to pause moving or animated text.

Allow users to delay update frequency.

Pause, stop, hideProvide all moving, blinking, scrolling, or auto-updating content with user controls.
Three flashes or belowRemove any content that flashes more than three times per second.
Bypass blocksAdd a “Skip to Content” link to all site pages.

Make the “Skip to Content” link visible and accessible.

Page titledWrite unique and descriptive titles for each page on your site.
Focus orderEnsure site functionality with the “Tab” key.

Make the order of elements, like pages on your navigation, logical.

Link purpose in contentCreate easy-to-understand anchor text that aligns with the surrounding text.
Page languageUse HTML to use the appropriate language code for pages.
On focusEliminate responses that happen automatically, like pop-ups, form submissions, and link openings.

Require a user action, like a mouse click to open a link, for responses to happen.

On inputRemove any auto-submit form fields.

Eliminate any instances that remove a user’s control when interacting with an element.

Error identificationProvider users with explanations for errors and instructions on how to fix those errors.

Place error explanations near the error, like a required, but blank form field.

Labels or instructionsLabel all input fields.

Describe the preferred format for input fields, like for a phone number or date.

Provide helpful instructions for completing input fields.

ParsingFollow proper HTML structure and guidelines.

Fix any HTML elements with duplicate attributes.

Name, role, valueEnsure site uses valid HTML markup.

Follow HTML specifications for website scripts.

Level AA website accessibility checklist

With the Level AA website accessibility checklist, your business takes a more proactive approach to building and maintaining an accessible site. Most action items on this website compliance checklist make your website accessible to almost every single user.

Level AA Web Accessibility Checklist
GuidelineWhat You Need To Do
Captions for live videosCaption live videos via software or professional services.
Audio descriptionAdd audio description soundtracks to any video content.

Provide a link to the soundtrack close to the content.

ContrastUse a light background and dark text or vice versa.
Resize textPrevent resized text from requiring users to scroll horizontally.

Enable resizing of text by up to 200%.

Text imagesEliminate any images that use images of text to convey content.

Use CSS to stylize text, like for pull quotes.

Finding pagesAdd an HTML sitemap.

Enable site search.

Create a logical navigation menu.

Make your navigation menu consistent across your site.

Headings and labelsMake headings and subheadings straightforward and descriptive.

Label site elements, like tables or forms.

Focus visibleUse CSS to add borders or underlines to elements when selected by a user’s keyboard.

Enable keyboard focus visibility on all site elements, like menus, form fields, and links.

Language of partsAdd a language attribute to pages with content that isn’t in your default language.
Consistent navigationAdopt a universal location for your navigation menu and order of items in the navigation menu.
Consistent identificationLabel and name elements with the same function consistently.

Use identical alt text for elements with the same function.

Error suggestionEnable elements, like forms, to identify input errors.

Communicate errors to users with text suggestions.

Error preventionMake changes to user-controlled data reversible, like canceling an order.

Allow users to correct errors.

Create a confirmation page that details the user’s input and the website’s outcome.

Level AAA website accessibility checklist

With Level AAA compliance, your business adopts an aggressive approach to website accessibility. While you can focus on this website accessibliyt checklist, it’s often considered too aggressive for most sites. That’s why many companies focus on Level AA.

Level AAA Web Accessibility Checklist
GuidelineAction Items
Sign languageUpload alternative video versions with sign language.

Place alternative versions near original video.

Extended audio descriptionCreate extended audio description soundtracks with enough pauses for users to listen and understand.

Place soundtracks near the original video.

Media alternativeWrite a full-text transcript.

Position the transcript near the video content.

Live audio-onlyUse closed captions.

Provide the script text.

ContrastUse a dark background and light text or vice versa.
Low or zero background audioEliminate background noise from audio.

Maintain a background noise 20 decibels below foreground noise.

Visual presentationUse tools that allow users to customize background and foreground colors, text spacing, and text size.
No timingAllow time limits for real-time events only, like auctions or live streams.
InterruptionsRemove redirects that happen after a specific amount of time.

Eliminate pop-ups.

Re-authenticatingSave users data, like items in their shopping cart, when re-authenticating their identity.
LocationUse breadcrumb navigation.

Add a sitemap.

Section headingsAdd relevant headings to content.
Unusual wordsAvoid idioms and jargon.

Explain words in-text or with a link to a relevant page.

AbbreviationsEliminate abbreviations or explain abbreviations in content.
Reading levelUse a readability testing tool, like Readable.

Create images or diagrams to explain content.

PronunciationLink to pronunciation guides for words or write the phonetic pronunciation.

Ready for WCAG compliance?

With this web accessibility checklist, your company (and team) can move forward with achieving WCAG compliance. If you need help, though, WebFX features a dedicated and experienced team of designers, developers, and copywriters.

Our website compliance services can help your business check off everything on your website accessibility checklist. Explore our plans today, and see why our recommendation score beats the industry average by almost 500%!

The post The Definitive Website Accessibility Checklist appeared first on WebFX Blog.

Share
Design Deals for the Week

Every week, we’ll give you an overview of the best deals for designers, make sure you don’t miss any by subscribing to our deals feed. You can also follow the recently launched website Type Deals if you are looking for free fonts or font deals.

140 Design Templates for FREE

Introduce: With Pikbest you’ll get everything you need about design, they provide millions of editable and printable templates like PSD files, Posters, Presentation, Sound Effects and Video for commercial use. Sign up and you could download 140 Templates free for two weeks.

Free VIP instead of $19.9– Get it now!

Kristopher: Elegant Serif Font with 475+ glyphs

Classically conservative, Kristopher can also be a more playful and modern serif font. With more than 475 glyphs, 150+ alternates, 12 ligatures and multilingual support, you can easily use this flexible font for any project from magazine covers to art posters.

$8 instead of $30 – Get it now!

1600 Premium, Customizable Infographics Templates

You’ll never need to worry about getting your point across again! Thanks to this collection of 1600 Infographics Templates, you can easily put together a colorful story through professional pictures and charts. Easily change up the text and any other details you’d like and you’ll quickly reach your audience in an entertaining and informative manner.

$24 instead of $750 – Get it now!

Procreate Lettering Starter Pack

With the Procreate Lettering Starter Pack you’ll get everything you need to start lettering on an iPad. Besides 35 different brushes, 25+ textures, 5 images and 2 color palettes, you’ll get a super helpful 10-part workbook that takes you through every step of the lettering process from letter anatomy to color theory to printing.

$9 instead of $25 – Get it now!


Thanks for being a subscriber, here is your FREE house vector icons set.

Share
Text-To-Speech And Back Again With AWS (Part 2)

Text-To-Speech And Back Again With AWS (Part 2)

Text-To-Speech And Back Again With AWS (Part 2)

Philip Kiely
2019-10-02T12:30:59+02:00 2019-10-04T08:08:33+00:00

This is the second half of a series on transforming content between text and speech on AWS. In part one, we used Amazon Polly to narrate blog posts and embedded the content in a website using an audio tag. In this article, we will use speech-to-text to draft transcripts of podcasts and interviews for publication. Finally, we will evaluate the overall accuracy of these format-transformation technologies by running a few samples through round-trip transcriptions.

Speech-To-Text Project

In 2012, Patrick McKenzie (a.k.a. patio11, of Kalzumeus and Stripe) and Ramit Sethi (of I Will Teach You To Be Rich) sat down and recorded two hour-long podcasts. As I am a fan of both of their work, I probably would have listened to the podcasts, but I definitely wouldn’t have listened to them several times each. The transcripts, on the other hand, I can reread and reference at my leisure. I also freely recommend the series when talking to people about freelancing, knowing that I am giving them a resource that takes a quarter the time to read that it takes to listen to. Even though the content of the podcasts and transcripts are exactly the same, the combination is 10× as useful as the podcast alone.

In the first transcript, McKenzie says that he paid 75 dollars and waited a couple of days to have the podcast transcribed by a professional service. His other option was to transcribe it himself. When I worked for my college’s newspaper, I frequently transcribed interviews. Over time, I got more practiced at the skill and improved from taking four minutes of transcribing per minute of audio to three minutes per minute. While I imagine that a professional with specialized equipment and a faster typing speed could drop below two minutes per minute, as an amateur transcriber McKenzie likely saved himself five or six hours of work by paying for the service.

Seven years later, it seems like he should have another option: an automated transcription with Amazon Web Services. As we’ll see, the transcription would require significantly more editing before it would be publication-ready, but automated transcription has two killer features compared to hiring a professional: he would have gotten the transcription back in real time for about a dollar. In this article, I’ll explain how you can use Speech-to-Text on AWS to easily make your content multi-format and ideas for using Amazon Transcribe in more complex applications.

Amazon provides a console to experiment with Transcribe. To access the console, log on to your AWS account and search “Transcribe” in the services search field. The console exposes the full power of Transcribe, and if you’re only planning on transcribing a few pieces of content per week then using the console is a solid long-term option. The transcription console gives you two options: streaming audio and uploading a file.

Amazon Transcribe Console Real-Time Transcription Tab
You can launch live transcriptions in the real-time transcription tab. (Large preview)

The “real-time transcription” tab offers the ability to speak into the microphone and have a transcription generated in real time. Speaking deliberately, and with my computer’s onboard microphone, I was able to transcribe the sentence “Smashing Magazine publishes technical content for developers worldwide” on the first try. However, when I tried to transcribe the previous paragraph at a more conversational speed and articulation, there were numerous errors.

“Amazon provides a consul to experiment with transcribe access. The console log onto a ws account and search transcribed in the services search field, The consul exposes the full power of transcribed. And if you only planning on transcribing a few pieces of content a week than using the consul is a solid long term option. The transcription Council gives you two options streaming audio and uploaded a file.”

In addition to simply missing some words, Transcribe has issues with homophones and punctuation. In the first sentence, it transcribed “console” as “consul.” This homophone error can only be corrected by evaluating each transcribed word in the context of the sentence and adjusting according to the algorithm’s best guess. The first sentence also runs into the second, which throws off the grammatical structure and meaning of the entire rest of the paragraph. Beyond contextual clues, Amazon Transcribe seems to use pauses to determine punctuation. That said, I am using a built-in microphone, transcribing in real time, and to be honest I don’t have the clearest speaking voice. Let’s see if we can find improvements by mitigating each of these factors.

I used a Blue Yeti, a midrange all-purpose recording microphone, to stream audio into the console. As you can see in the image below, improved audio quality did not significantly improve transcription quality. I hypothesize that while a poor quality audio input would further degrade the text’s accuracy, improvement past the threshold of a built-in microphone or cheap webcam does not provide the quality transcription that we are looking for.

Results of using a good microphone
Improving microphone quality does not materially improve transcription quality. (Large preview)

Using the same microphone, I recorded the same paragraph as an .mp3 file and uploaded it for transcription. To do the same, navigate to the “Transcription Jobs” panel and click the orange button with the text “Create Job.” This will bring you to a form where you can configure the transcription job.

Transcription job form top half
A transcription job requires a title, language, input source, and file format. (Large preview)

The job name is arbitrary, just choose something that will be meaningful to you when you review the completed jobs. You can select from about a dozen languages, with English and Spanish available in regional variants. The transcription service draws its input from S3, so you’ll need to upload your audio file to the storage service before you can run the job. You can upload the file in one of four supported formats: .mp3, .mp4, .wav, and .flac.

Transcription job form bottom half
A transcription job offers data location and audio identification options. (Large preview)

If you want to keep the output data in a permanent location, change “Data location” to “Customer specified” and enter the name of an S3 bucket that you can write to. Finally, you can choose between two identification options. Channel identification tags input with the channel that it came from in the audio file, while “Speaker identification” attempts to recognize distinct voices in the audio. If you are transcribing a multi-person podcast or interview, Speaker identification is a useful feature, but it is not applicable to this simple test.

Inspecting the output, unfortunately, reveals that the transcription is no more accurate than the real-time console transcription. However, running a transcription job does provide more data. In addition to the transcription text, the job outputs JSON with each word, its confidence score, and alternate words considered, if any. If you want to write your own natural language processing code to try to improve the readability of the output, this data will give you what you need to get started.

Finally, I had a friend who hosts a local radio show narrate the same paragraph for live transcription. Despite his steady pace and clear enunciation, the resulting text was no more accurate than any of my live transcription attempts. While a professional narrator may be able to achieve even more specific pronunciation, the technology is really only useful if it is widely usable.

Unfortunately, it seems that the transcription quality is too low to fully automate our proposed use case. Depending on your typing speed, running audio through Amazon Transcribe and then editing by hand may be faster than simple manual transcription, but it is not a turnkey solution for speech-to-text that compares to what exists for text-to-speech. For specific domains, you can define Custom Vocabularies to improve transcription accuracy, but out of the box, the service is insufficiently advanced.

As with most of its services, AWS offers an API for using Transcribe. Unless you have a large number of files to transcribe or you need to transcribe audio in response to events, I would recommend using the console and save yourself the time of setting up programmatic access.

To use Transcribe from the AWS CLI, you’ll need a JSON file and a terminal command.

aws transcribe start-transcription-job 
     --region YOUR_REGION_HERE 
     --cli-input-json YOUR_FILE_PATH.json

At YOUR_FILE_PATH.json, you’ll need a .json file with four pieces of information. As above, you can set any meaningful string as the TranscriptionJobName and any supported language as the LanguageCode. The CLI supports the same four media file formats and still reads the media file from S3.

{
    "TranscriptionJobName": "request ID", 
    "LanguageCode": "en-US", 
    "MediaFormat": "mp3", 
    "Media": {
        "MediaFileUri": "https://YOUR_S3_BUCKET/YOUR_MEDIA_FILE.mp3"
    }
}

This kind of access is also available through a Python SDK. Amazon recommends Transcribe for voice analytics, search and compliance, advertising, and closed-captioning media. In each of these cases, the transcribed text is an input to another system like Amazon Comprehend rather than the final output. Thus, as a developer, it is important to design your system and limit its use cases to tolerate the range of errors that Transcribe will feed into your application.

Note: For more on using Amazon Transcribe and other services programmatically, check out Amazon’s getting started guide.

Round Trip Accuracy

While the live performance of Amazon Transcribe was somewhat disappointing, we can investigate the theoretical maximum accuracy of the system by transcribing something that was read by Amazon Polly. The two services should be using compatible pronunciation libraries and speech cadences, so text input into Amazon Polly should survive the round trip more or less intact. Of course, we will stick with the same test paragraph.

Lo and behold, this is the only strategy that has made the transcription noticeably better:

“Amazon provides a console to experiment with transcribe. To access the console, log onto your AWS account and search transcribing the service’s search field. The console exposes the full power of transcribe, and if you’re only planning on transcribing a few pieces of content per week than using the console is a solid long term option. The Transcription council gives you two options. Streaming audio and uploading a file.”

Stubborn errors persist (“council” versus “console” comes in at 70% confidence) but overall the text is a few edits away from useable. However, most of us don’t speak like synthesized robots, so this quality is unavailable to us at the time of writing.

Conclusion

While the quality of output speech and text are noticeably lesser than that of a person, these services cost so little that they are a strong alternative for many applications. Text-to-speech, at 4 dollars per million characters (16 dollars per million for the superior neural voices), can narrate articles in seconds for pennies. Speech-to-text, at .04 cents per second, can transcribe podcasts in minutes for about a dollar. Of course, prices may change over time, but historically as technologies like these improve, they tend to become less expensive and more effective.

Because of the low cost, you can experiment with these technologies for things like improving your personal productivity. When biking or driving to work, it is impossible to type notes or an outline a project, however, speaking and automatically transcribing a stream-of-consciousness narration would get a lot of planning done. Journalists frequently transcribe long interviews, a process which AWS can automate by tagging the voices of people speaking in a recording. On the other side of the writing process, having a steady, robotic voice read your work back to you can help you identify errors and awkward phrasing.

These technologies already have a number of use cases, but that will only expand over time as the technologies improve. While text-to-speech is reaching near-perfect accuracy in pronunciation, especially when assisted by pronunciation alphabets and tags, the synthesized voice still doesn’t sound fully natural. Speech-to-text systems are pretty good at transcribing clear speech but still struggle with punctuation, homophones, and even moderately quick speech. Once the technologies overcome these challenges, I anticipate that most applications will have a use for at least one of them.

Smashing Editorial (dm, yk, il)

Share