I'm new to IBM Watson SpeechToText and I need to use it in a project but I've seen that the returned transcription doesn't have any punctuation. I've enabled smart formatting but it doesn't work.
Any suggestions?
For US English, the feature also directs the service to substitute punctuation symbols for the keyword strings in the audio.
IBM docs
Hi #l22dev the service does not provide punctuation at the moment, punctuation is not part of the smart formatting feature.
Related
I am trying to understand how a jump between skills should be handled in Botium Box. I am testing the dialogues of my Watson Assistant skills and I am noticing something weird.
Differently from the jumps within one skill, where each row of my input test file (in my case excel file) contains the text of a different node, when I do a jump between skills, it seems like the text of the nodes is concatenated, and therefore to make the test case passing I should write all the text in one row of my excel file (very difficult to maintain)
If that is the case, how do I concatenate normal text and utterances variables? Is there a command for that? Or am I missing something in the configuration of my botium box?
While I don't know where the described behaviour is coming from, here are some comments:
Usually, one Watson Assistant is linked to one Dialog skill (and, for Plus plans, optionally a search skill). Botium can either connect to
an assistant by using the Watson Assistant V2 SDK
or a skill by using the Watson Assistant V1 SDK with the Skill legacy mode
If you plan to use multiple skills in your chatbot, then you have to develop some code to switch between the assistants - this is called an Orchestrator in IBM terms, and you can find example code by IBM here.
In this case, the best option you have in Botium is to use the Generic HTTP/JSON Connector to connect to the API of the Orchestrator, instead of going directly to Watson APIs.
I wrote about a similar topic - how to choose a Botium connector - in my blog.
Florian, thanks for your reply. It is clear to me the concept of the orchestrator and I am actually using it as well as the HTTP/JSON Connector.
My question is more about how to write test cases in excel files that include both normal text and Utterances variables. For example, if I have in the utterances files:
utterance file
Can I have in my test case something like:
test case with text and utterance variable
If that is the case, what is the key word needed to concatenate the text ("hello") and the utterance variable (GREETING)?
I think the title explains my doubt.
I've tried before the Speech to Text feature from Azure.
The question is:
Is there a way to use the sound binary to Azure LUIS instead of the text?
Yes, LUIS can accept speech input instead of text. LUIS provides this tutorial on how to setup speech services. The tutorial is in C#, however it appears their GitHub repo has samples in other languages, if of use.
Hope of help!
if you are creating a speech bot, here is a new approach.
so it leverages azure speech (TTS and SR), integrate with bot service in a more easy way
https://learn.microsoft.com/en-us/azure/bot-service/directline-speech-bot?view=azure-bot-service-4.0
I want to find the way how can I connect Speech Translation with Custom Translator.
On Custom Translator webpage there is mentioned that: "Custom Translator can be used for customizing text when using the Microsoft Translator Text API , and speech translation using the Microsoft Speech services."
Unfortunatelly, I didn't find any example of that usage.
Can anyone help with that?
Thank you!
If you build your application based on this example,
You can set the category id at the SpeechTranslationConfig as follows:
config->SetServiceProperty("category", "", ServicePropertyChannel.UriQueryParameter);
This is available since Microsoft Speech SDK 1.5. details
This article references a feature called "Word Hints." But I am not able to find more info on how to use that. Anyone run into this?
https://cloudplatform.googleblog.com/2016/07/the-latest-for-Cloud-customers-machine-learning-and-west-coast-expansion.html
Word hints are available for the Speech API (docs here) but this feature is not currently supported for the NL API.
We are discussing a project where we need to identify if a word is a noun, verb, pronoun etc. At the same time, we need to check a sentence if that is correct (grammatically).
This is a huge task to do from scratch, so I am wondering if there is any service/api available for this?
The application will be android based either native or phonegap based, so api compatible with the major languages will help immensely.
LanguageTool has an HTTPS API (disclosure: I'm the LanguageTool maintainer) for text checking. The part-of-speech information is available via its Java API, not via HTTP.