Are you thinking about creating a speech bot-driven app for your business? Some of the guidelines around bot creation—as outlined at Microsoft Build by noted Swedish entrepreneur, podcaster, and Windows Platform Development MVP Jessica Engstrom—are common sense. For example, don’t build a voice bot just because it’s cool new technology, and make sure it fits your business model.

But there are plenty of scenarios where voice does fit. One argument is that the average person types 40 words per minute but speaks 150. Approximately 3,000 new bots are released per week on the Microsoft platform alone, and 95 percent of smartphone owners have tried a personal assistant.

It’s not all smooth sailing, though. Engstrom mentioned Microsoft’s own disastrous voice-plus-AI experiment, Tay, which the company had to pull in less than a day after the internet taught it to be racist. And she pointed to Burger King, which ran a commercial designed to trigger Google Home but instead read a Wikipedia page saying the Whopper contained cyanide.

When designing a voice assistant, you should limit the scope of possible answers, Engstrom said. Don’t have it ask open-ended questions. Train the voice assistant to handle many ways of phrasing a question or command. Even write a full script of a conversation that makes sense for your bot. Finally, provide audio help, giving examples of what kind of things a user can say.

New for Azure Speech Technology

One of the big announcements at the Build Keynote was the ability to transcribe multiparty speech in meetings while keeping track of which speaker said what. In a separate session, Aarthy Longino, Principal Program Manager for Speech and Language at Microsoft, showed this working in a custom development interface.

At last year’s Build, the biggest hit was a meeting “cone” that recognized participants and transcribed what each said. Now that cone, which also sports a 360-degree camera, is being tested by Microsoft customers in private preview. But there are other devices that anyone can get to test the transcription, including the Roobo Smart Audio Dev Kit, which was impressively demoed in the session.

You can find these Cognitive Services Speech Devices at aka.ms/sdsdk-get.

On the other end of speech, and at least as impressive, is text to speech (TTS). Microsoft’s Qinying Liao, a Principal Program Manager on Speech Services, showed advances in things like the remarkably natural-sounding new Neural Voices, which was so smooth that attendees in the room voted for it over an actual human reader.

Currently, Neural Voices are only available for nine regional English dialects, but Japanese, Spanish, and Portuguese are in the works.

Another new capability is to add emotion to the TTS: a simple keyword in code can make the generated voice sound cheerful or empathetic. That works the other way, too. In fact, Microsoft’s transcription technologies for call centers can detect when an interaction starts to go negative. The Speech Services will let businesses customize recognition and TTS using their own terminology in a new Custom Speech Portal. You can read about all the Azure Speech Services at this help page.

This article originally published at PCMag
here

Google went out of its way during I/O to emphasize the ways it’s trying to make its products more accessible. One project that could have a huge impact: Live Captions, a new feature coming to Android Q.

The feature automatically surfaces captions to any video or audio content on your phone in real time, regardless of whether you’re online or off. 

That would make just about all video and audio content — including video calls, audio messages, and podcasts — accessible to people who are deaf or hard of hearing. It would also benefit everyone who occasionally watches videos with the sound turned off. That this can happen instantly on your phone without a data connection is all the more impressive — provided Google can pull it off.

SEE ALSO: What will Google call Android Q? We have some ideas.

Google hasn’t given it a launch date, though it says the feature will be available as part of Android Q. But I got the chance to try it out and I walked away mostly impressed, though it’s clear there are some issues that need to be addressed.

When the feature rolls out, the idea is for Live Captions to be available throughout your phone regardless of what app you’re using, so you can call them up any time there’s audio playing. Whether you’re watching a video or listening to a podcast, all you do is press the volume down key to bring up the Live Captions button.

One of the most impressive aspects of the technology is that captions begin appearing almost immediately, even when you’re offline. (Like many other new features Google announced at I/O, Live Captions does all of its processing on the device itself, so no connection is needed.) My entire demo was on a phone that was in airplane mode and not connected to WiFi. 

As for the actual captioning, well, it’s clearly still very much a work in progress. When my colleague Raymond Wong and I tried it out with videos of us speaking, we got mixed results.

When we were in a quiet room, and kept the phone’s microphone close, the results were damn near flawless. Though the captioning system struggled with a word here or there (“hashtag” seemed to throw it off), its accuracy was otherwise impressive. 

But, move the phone a few inches away from the speaker, and things were much less consistent. It misidentified a number of words even though the audio in the video was clear. These issues were even more pronounced when we tried out Live Captions in a room with a lot of background noise. In one instance, the captioning system generated significantly different text for the same video within the span of a few seconds.  

A Google spokesperson reiterated that it’s still early for Live Captions and that the team behind it is still making improvements. That’s true of any pre-release software, but it will be especially important for Google to address the issues we experienced. 

Not all audio is perfectly crisp and clear. Some people mumble or have accents. We share video from noisy places or with many people speaking. While it’s understandable these issues would be more difficult to address, it’s important they are fixed, as it’s more representative of the way people actually use their phones. If Live Captions can’t work reliably in these scenarios, it will be much less useful and risks becoming an afterthought.

Still, if Google can make it reliable, Live Captions would make a dramatic difference for the people who need it most. Let’s hope they get it right.