Slashdot Mirror
Siri, Cortana and Google Have Nothing On SoundHound's Speech Recognition
MojoKid writes: Your digital voice assistant app is incompetent. Yes, Siri can give you a list of Italian restaurants in the area, Cortana will happily look up the weather, and Google Now will send a text message, if you ask it to. But compared to Hound, the newest voice search app on the block, all three of the aforementioned assistants might as well be bumbling idiots trying to outwit a fast talking rocket scientist. At its core, Hound is the same type of app — you bark commands or ask questions about any number of topics and it responds intelligently. And quickly. What's different about Hound compared to Siri, Cortana, and Google Now is that it's freakishly fast and understands complex queries that would have the others hunched in the fetal position, thumb in mouth. Check out the demo. It's pretty impressive.
The iPhone is the same way. I finally realized the correct response is "yeah."
I take it you don't know what a homophone is so you relied on some website to check for you?
Because if you actually read what GP wrote you might notice that "waze" (which is not a dictionary word) sounds identical to "ways" (which is a dictionary word). Depending, of course, on how you pronounce ways. But a native English speaker (are you?) is almost certainly going to pronounce "waze" identically to "ways".
Whether or not this would actually result in a problem with the app being slashvertised is a different matter entirely. But I hope you have a somewhat better understanding of what homophones are and how this could be seen as a problem for such an application.
I use Siri to text fairly regularly, and know the following affirmative responses work to confirm sending:
Yes
Yep
Yup
Yeah
Sure
Yes please
Affirmative
Please do
The following work sometimes, but not reliably:
Uh-huh (Sometimes interpreted as Uh-Uh)
Obviously, YMMV.
First, the video is speedup. Install the application yourself and the speed is lower, you can even notice it in the video by both voice.
Secondly, the backend is the Wolfram Alpha, hence you get very statistical answers easily and quickly, but nothing else really.
population of capital of the country
And Washington DC is the capital of the United States, the country where the Space Needle is located.
Feel free to give it a try yourself:
https://play.google.com/store/...
Currently we are on an invite system, but a lot of people have received invites.
Yes I work for SoundHound ;)
Actually you can increase the speed of the speaking voice on Android in Settings -> Language & input -> Text-to-speech output -> Speech rate, that's what was done for this video. The recording is at normal speed.
Feel free to test it yourself, you'll notice the results are completely different from Wolfram Alpha:
https://play.google.com/store/...
Just cleaning up the FUD, yes I work at SoundHound ;)