Azure AI Speech

Is there a way to get begin time and end time for the conversion result of stream audio?

I am using azure-speech to recognize audio stream, from speech_recognition_samples.cpp, from class RecognitionResult I only can get the Text and m_duration, but how can I get the begin time and end time of the result in the speech? I use azure-speech…

Should I use C++14 to compile Azure ASR project?

In the samples, C++14 is being used, while the guidance says Speech SDK uses C++ 11 standard. When I use the c++11 following guidance, I will get error: speechapi_cxx_conversation_translator.h:349:26: error: invalid user-defined conversion from…

Pronounciation issues for some words for french (CA) and english (CA)

Hello, Some frequently used words from French and English are mispronounced by azure for Canadian region. Here is a list, we are still able to make it work by using lexicons, but it would be better for all users if those were fixed. French (Sylvie…

Speech Custom Keyword Training Data

I am looking at the Custom Keyword feature in Speech Studio. On several places it is hinted that you can add external training data On https://speech.microsoft.com/customkeyword it states the model is always improving as more data is added On…

Training Custom Speech model

I have faced below error When Training Custom Speech model . Data uploading and testing was succeeded. Are there any way to check what happen on this Custom Speech Error message: Internal server error. Please recreate the task in a while. If the…

How can I use Azure speech to recognize audio stream with c++, is there any samples?

I have two questions: 1 From I did not find sample about audio stream. 2 I have replaced scriptionKey and ServiceRegion, and subscribed Speech Service, I tried this std::string FILE_NAME = "./myVoiceIsMyPassportVerifyMe03.wav"; void…

How do i set up the audioConfig right with my Microphone?

Hey, im trying to set up a recognizer in order to record my microphone. The mic gets detected and the session starts. Buts thats it. using System.Collections; using System.Collections.Generic; using UnityEngine; using System; using System.IO; …

Sample utterances files

Hi, Are there any examples available for utterance files to be uploaded? It would be good to have a list that works well. Thanks,

Word Offset By Result.Text and not LexicalForm

Support, Issue #1 So in order to track audio with outputted text, I need the e.Result.Best().words to be the e.Result.Text words to be the same. Example: Say "James Bond 007" is e.Result.Text e.Result.Best().words is an array of…

How can we customize TTS/STT for a rare language?

There are so many languages and dialects that have no standard of pronunciation and writing system. If we want to customize a certain unstandard languages. How many steps should we take? Is there any notifications for those who want to customize a rare…

Why my testing always failed in Custom Speech?

Get voice profile by profile id using NodeJS

Hi, I would like to get the voice profile by the profile id using NodeJS and do future enrollment and verification. Can I simply call new VoiceProfile(profileId: string, profileType: VoiceProfileType) to retrieve the profile? Thanks in advance!

Is the text to speech service overrrides the diacritic on Arabic words?

Hello, I am trying the text to speech service with the following options: Language: Arabic (Egypt), Voice: Salma Neural. I tried to add a sentence with full diacritics. The output audio does not stick to the diacritics added on the words and pronounce…

Speech Studio - cannot test audio data

Hello, I am using the Speech Studio to test some audio data with human labeled transcript for Word Error Rate. I get "failed" after I perform a test, I tried with multiple audio data, even the example from Microsoft. I get following error: …

how to lock down the access to speech resource to Speech portal only?

how to lock down the access to a speech resource so that only Speech portal (speech.microsoft.com) would get access to it? Currently the resource requires "access from all networks". This is against our policy. How can we lock this down? I…

Documentation error: Audio Content creation: UTF8-BOM required

Today I found out, that uploads of SSML files containing language specific characters (here: Danish), it is only possible, if you convert it to UFT8-BOM (e.g. with notepad++). Only a generic error message is displayed "file format error",…

Managing larger numbers of TTS files in Audio content creation: Search and download all functions missing

When managing larger amount of generated TTS files in Speech studio / Audiocode Content Creation with multi-page lists of TTS files, there is no search function and no function to download the whole folder. You can only download page per page. The portal…

Battalion is misspelled in the speech-to-text return

I'm working on audio data files that have a lot of radio chatter between fire departments. The word "battalion" often comes up, and the speech-to-text misspells it every time as "battallion". Here is an example audio file with…

ALSO Speech tasks stuck in PROCESSING

Text to speech audio conversion has been processing a 2 minutes audio for more than 20 hours. I cannot work on the next audio or delete the one still processing.

Continue Speech Recogonization with Custom keyword

Hi , I am going to develop voice recolonization in this i have two custom keyword and more than 20 custom Command. so i have created custom keyword on my studio login and downloaded .table file and i am checking user voice with .table file locally that…

Azure AI Speech

Azure AI Speech

An Azure service that integrates speech processing into apps and services.

1,516 questions

Sign in to follow

Universal Windows Platform (UWP)

Universal Windows Platform (UWP)

A Microsoft platform for building and publishing apps for Windows desktop devices.

2,889 questions

Sign in to follow

C#

C#

An object-oriented and type-safe programming language that has its roots in the C family of languages and includes support for component-oriented programming.

10,573 questions

Sign in to follow