What May be Unique in Voice Queries?
Might a twang or a drawl influence the search results you see at Google? If you’re prone to calling an elevator a lift and tend to speak the Queen’s English in an accent similar to hers, you might see different search results than if you grew up in the Bronx or in New Orleans. If you sport a Polish accent or a Spanish one, and you perform voice queries on your phone, would receiving results in Polish or in Spanish because of your accent be a problem or a benefit? If your accent is Australian, and you search for “football” while in the US, would it surprise you to see some Australian Rules Football results returned to you?
Search engines have been using something called an Automated Search Recognition (“ASR”) engine to try to eliminate or reduce accents in voice queries by treating those as if they were noise. But the value of that noise might also be recognized as another signal that might improve search results.
A new patent was granted to Google yesterday that explores accents within voice queries in more depth. For instance, it provides this example of how a search engine might use such accent information:
By including the accent of a voice query as an input to the search result generation process, search result rankings can be biased to offer preferred results to accented voice queries.
For example, if English-language speakers with a French-language accent show a preference for a particular result for the query terms “restaurants in Scranton” than do English-language speakers with a Russian-language accent, a search engine will be more likely to select that particular result for another user who provides a voice query in the English language with a French-language accent. The preference for that particular search result would not be reflected in search results that are generated for other users that do not have that particular accent.
Such a process would be a data-driven one that could start collecting accent information when speech-based queries are made to possibly influence future search results and rankings as well. The patent tells us that accents can be indications of common backgrounds, native languages, and/or regions of origin.
The patent is:
Accent-influenced search results
Invented by Barry Hayes
US Patent 8,417,530
Granted April 9, 2013
Filed August 20, 2010
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating search results. In one aspect, a method includes obtaining a transcription of a voice query, and data that identifies an accent of the voice query, submitting the transcription and the data that identifies the accent of the voice query to a search engine to generate one or more accent-influenced results of the voice query, and providing the accent-influenced results to a client device for display.
Voice Queries Take-Aways
I’ve had friends over the past 10 years or so experiment with voice recognition software with varying degrees of success. We know that Google provided a free voice search service named GOOG-411 for a number of years to collect as much data as they could about voice searches. What I hadn’t considered was that in addition to collecting data about how to filter out accents, it was also likely that they were also collecting information about those accents as well.
It seems that the noise Google was filtering out of voice queries now has the chance to be the signal that Google might use to filter search results with.
I look forward to experimenting with my large repertoire of accents. I’m especially good at Welsh and Deep South.
Hi Bill,
It will be interesting to see what my Icelandic accents returns in my search. I’m however not sure I want Google to make that kind of decisions for me.
Thanks,
Anita Sig Happiness Therapist
That is interesting. I can see the benefit of this and I also wonder how google will balance this with geo-location filters. For example, what if someone in the US (let’s say a football stadium) searches for “football” with an australian accent. Would Google assume that they are looking for US rules because they are at a US game? IDK, but this is an interesting topic to consider.
I still get some interesting and strange responses from voice recognition tools like siri so it will be interesting to see how this develops. Although there has been some development over the last 10 years in this field as you mentioned there have been varying degrees of success and I don’t see it has progressed as fast as other technology. Google seems obsessed with second guessing a persons location but what if you have an Irish accent but looking for a Chinese restaurant in New York? When travelling now I get constantly frustrated with Google confronting me with search results and ads in the language of the country I am in and asking if I want to see results from the Google version for that country and vice versa when I return home. It’s already a problem that might get worse with this accent recognition.
I love the renewed efforts to perfect this technology. It seems like the last time someone took a real swing at it was when DragonSpeak was still a product.
For me, I live in a state with no cell phone while driving laws. If my voice-to-text was more accurate, I could be much safer.
This is absurd. Actually, it fringes on stereotyping.
Hi Matt,
I’m not sure how you might construe this as stereotyping, except for the fact that the results that would be returned to someone might be based upon an accent.
If you look up the definition of “stereotype,” if often refers to widely held belief about a particular group of people that is often over-generalized. That’s not the point behind this patent. Instead, it considers the use of an accent as additional data that might be used when deciding upon and filtering search results.
We don’t know if Google ever adopted this for use.
If you do feel that this patent does fringe on stereotyping, I’d be happy to hear your argument about it, based upon the actual patent itself rather than my blog post about it. Thanks.
I tried too by saying football ïŠ it was really surprising result. In my personal opinions it is still needed to update in accent point of view as some time it get verse instead of helping and people get struck in to the results instead of getting accurate ones instantly.