I was investigating various Speech Recognition strategies and I liked the idea of grammars as defined in the Web Speech spec. It seems that if you can tell the speech recognition service that you expect “Yes” or “No”, the service could more reliably recognize a “Yes” as “Yes”, “No” as `No”, and hopefully also be able to say “it didn’t sound like either of those!”.
However, in SFSpeechRecognitionRequest, I only see taskHint with values from SFSpeechRecognitionTaskHint of confirmation, dictation, search, and unspecified.
I also see SFSpeechRecognitionRequest.contextualStrings, but it seems to be for a different purpose. I.e., I think I should put brands/trademark type things in there. Putting “Yes” and “No” in wouldn’t make those words any more likely to be selected because they already exist in the system dictionary (this is an assumption I’m making based on the little the documentation says).
Is a way with the API to do something more like grammars or, even more simply, just providing a list of expected phrases so that the speech recognition is more likely to come up with a result I expect instead of similar-sounding gibberish/homophones? Does contextualStrings perhaps increase the likelihood that the system chooses one of those strings instead of just expanding the system dictionary? Or maybe I’m taking the wrong approach and am supposed to enforce grammar on my own and enumerate over SFSpeechRecognitionResult.transcriptions until I find one matching an expected word?
Unfortunately, I can’t test these APIs myself; I am merely researching the viability of writing a native iOS app and do not have the necessary development environment.
Related
I am working in an application that gathers a user's voice input for an IVR. The input we're capturing is a limited set of proper nouns but even though we have added hints for all of the possible options, we very frequently get back unintelligible results, possibly as a result of our users having various accents from all parts of the world. I'm looking for a way to further improve the speech recognition results beyond just using hints. The available Google adaptive classes will not be useful, as there are none that match the type of input that we're gathering. I see that Twilio recently added something called experimental_utterances that may help but I'm finding little technical documentation on what it does or how to implement.
Any guidance on how to improve our speech recognition results?
Google does a decent job doing recognition of proper names, but not in real time just asynchronously. I've not seen a PaaS tool that can do this in real time. I recommend you change your approach and maybe identify callers based on ANI or account number or have them record their name for manual transcription.
david
I'm using on-device speech-to-text in my app, and I was hoping to use contextualStrings to help it recognize some more niche vocabulary. However, it never recognizes any of the words. I am following all of the guidelines they outline here, but they never seem to be recognized when I have requiresOnDeviceRecognition set to true. They do get recognized when I set requiresOnDeviceRecognition to false, however. Is it because the Speech-to-Text engine is better with it off? Or does contextualString require the internet to work? I couldn't find any documentation saying it needs internet.
Example:
...
private let contextualStrings = ["hipaa", "cologuard"]
recognitionRequest.contextualStrings = contextualStrings
Hipaa always becomes hyppa for some reason (which isn't even a word on the system vocabulary?)
Interestingly, if I were to say "HIPAA violation" does HIPAA actually get recognized by the on-device speech-to-text engine. This seems to be only time it ever works
I have a service that allows user's (admins) to change the terminology the site uses. My designer wants me to use the format "A Group". The problem is, for some terminology, it should be "An" not "A".
Is there any way to reliably detect which to use? What about localization?
I can brute force it and get 90% of the way by checking the first letter for consonant vs vowel. That won't work for all words though. And that doesn't cover any language except English.
In my opinion you've got only 2 ways:
1- You need to check the first letter and process all the sentence by checking its letters to see if there is any non-English letters.
2- Provide a dictionary of English nouns then you can easily check your word to find if it needs an "a" or "an".
Although the "a versus an" issue is very specific, what you're describing here is a natural language processing issue. Essentially you are being asked to write code that generates a grammatically correct piece of text.
I think you should try to to explain the implications to the designer, especially if you end up localizing in other languages. Your time is probably better spent working on your app's business logic than on language processing.
I have a slightly unusual profanity-related question.
Now we're used to dealing with profanity-filtering of user-generated content — any method is imperfect, but products like CleanSpeak and WebPurify do a good-enough job.
The problem we have at the moment, though, is that we've been building an engine to run promotional-code–based competitions, that will be used internationally. We could do with checking that none of these codes is profane in Latin American Spanish or Malay (at least in the first instance), to make sure we don't send out a code that's equivalent to FUCK23 or PEN15 or something.
We've tried Googling around and asking people we know, but we can't find an easy way of getting hold of an es-419 or an ms profanity list to filter the codes against. As there are literally millions of codes per locale, we'd rather do an offline check than hit an API for each code (which would be expensive both in terms of bandwidth and usage fees).
I know this is a bit of a long shot, but does anyone know of a good source for profanity lists in different languages?
#disclaim: We know that no profanity filtering is perfect, that it's essentially futile with user-generated content and we have read SO #273516: How do you implement a good profanity filter? — that's not what we're asking.
Building or finding lists in other languages is extremely time consuming and difficult (trust me, we've built many of them at Inversoft). You might be better off tweaking the code generators instead (from what I could tell your code is generating the promotional codes rather than humans).
The best way to tweak a generator is to ensure that the codes can't easily form words based on the general use of consonants and vowels in most European languages. Things get a bit dicey in Polish and others, but it usually works.
Generally, most codes that start with a vowel are followed by another vowel or a non-joining consonant (like 'q' without a 'u'). If the code starts with a consonant then the next character is the same consonant or one that has a low probability of being used. For example, if you start with 's' then adding 'g' is a good choice.
You could also use wiktionary or other similar sources (like Linux dictionary files) to build a statistical approach to this. By extracting the probability of characters being next to each other, you should be able to generate codes with good accuracy of never being words in any language.
However, if I misread your question and you aren't generating the codes programmatically, you can ignore my response completely. :)
I have had the same thoughts. in trying to generate 6 character codes for a project i am doing.
I decided to reduce the likelyhood of obvious porfain codes So i removed the vowels that i found in as many "bad" words as i could think of, from my intial base 36 generation code. Leaving me with something more like a base 28 system that did not include a,e,i,o,u, 1,0. the one and zero were removed to reduce confusion between those characters in some fonts with I,L,O's
so far I have not seen a "profain" code genreated. Although base 28 has 1.something billion unique combinations.
i cannot vouch for other languages, and had not even considered it...
I am searching for an algorithm to determine whether realtime audio input matches one of 144 given (and comfortably distinct) phoneme-pairs.
Preferably the lowest level that does the job.
I'm developing radical / experimental musical training software for iPhone / iPad.
My musical system comprises 12 consonant phonemes and 12 vowel phonemes, demonstrated here. That makes 144 possible phoneme pairs. The student has to sing the correct phoneme pair 'laa duu bee' etc in response to visual stimulus.
I have done a lot of research into this, it looks like my best bet may be to use one of the iOS Sphinx wrappers ( iPhone App › Add voice recognition? is the best source of information I have found ). However, I can't see how I would adapt such a package, can anyone with experience using one of these technologies give a basic rundown of the steps that would be required?
Would training be necessary by the user? I would have thought not, as it is such an elementary task, compared with full language models of thousands of words and far greater and more subtle phoneme base. However, it would be acceptable (not ideal) to have the user train 12 phoneme pairs: { consonant1+vowel1, consonant2+vowel2, ..., consonant12+vowel12 }. The full 144 would be too burdensome.
Is there a simpler approach? I feel like using a fully featured continuous speech recogniser is using a sledgehammer to crack a nut. It would be far more elegant to use the minimum technology that would solve the problem.
So really I'm hunting for any open source software that recognises phonemes.
PS I need a solution which runs pretty much real-time. so even as they are singing the note, firstly it blinks on to illustrate that it picked up the phoneme pair that was sung, and then it glows to illustrate whether they are singing the correct note pitch
If you are looking for a phone-level open source recogniser, then I would recommend HTK. Very good documentation is available with this tool in the form of the HTK Book. It also contains an entire chapter dedicated to building a phone level real-time speech recogniser. From your problem statement above, it seems to me like you might be able to re-work that example into your own solution. Possible pitfalls:
Since you want to do a phone level recogniser, the data needed to train the phone models would be very high. Also, your training database should be balanced in terms of distribution of the phones.
Building a speaker-independent system would require data from more than one speaker. And lots of that too.
Since this is open-source, you should also check into the licensing info for any additional details about shipping the code. A good alternative would be to use the on-phone recorder and then have the recorded waveform sent over a data channel to a server for the recognition, pretty much something like what google does.
I have a little bit of experience with this type of signal processing, and I would say that this is probably not the type of finite question that can be answered definitively.
One thing worth noting is that although you may restrict the phonemes you are interested in, the possibility space remains the same (i.e. infinite-ish). User training might help the algorithms along a bit, but useful training takes quite a bit of time and it seems you are averse to too much of that.
Using Sphinx is probably a great start on this problem. I haven't gotten very far in the library myself, but my guess is that you'll be working with its source code yourself to get exactly what you want. (Hooray for open source!)
...using a sledgehammer to crack a nut.
I wouldn't label your problem a nut, I'd say it's more like a beast. It may be a different beast than natural language speech recognition, but it is still a beast.
All the best with your problem solving.
Not sure if this would help: check out OpenEars' LanguageModelGenerator. OpenEars uses Sphinx and other libraries.
http://www.hfink.eu/matchbox
This page links to both YouTube video demo and github source.
I'm guessing it would still be a lot of work to mould it into the shape I'm after, but is also definitely does do a lot of the work.