Saving audio stream generated by azure speech service ...
Hi, I am having hard time saving AudioDataStream generated by Azure TTS to a wave file using the method AudioDataStream.SaveToWaveFile(filename) for my Xamarin.Forms App. I am not sure what scheme to use for the filename parameter of the…
We would like to know noises effect to speech to text performance
Hello. We are using Azure Japanese speech to text. We want to evaluate its performance. What parameters affect the result, noises or microphones or intonations or etc....?
problem of running speechSynthetiser on aspx page
Hello, I've got a problem of running System.Speech.Synthesis.SpeechSynthetiser on aspx page. on a computer with windows 10 installation the control is operationnal but on a server with windows vista the same program with the same aspx and aspx.cs pages,…
Controlling speech pace dynamically
Hi all, I'm trying to control my speech pace (making it faster or slower) dynamically in my program. Is there any way to do it without using an SSML file? I'm using Java for Android. Thanks in advance.
Loading all intents from LUIS intent recognizer
I am using LUIS with speech input according to: https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/quickstart/python/intent-recognition/quickstart.py But ran into two problems, would be great if anyone has any advice: * Is there…
Can Azure Japanese Speech to Text provide the hiragana (phonetic) transcription?
I would like to use voice to enter the names of people in hiragana, by default the highest confidence prediction seems to select the most plausible Kanji for that name, but it would be more useful if it gave me the hiragana (phonetic sound) of the name.…
Speech to Text Error
Why am i getting this error, when I am trying to create a Resource for Speech to Text AzureSpeechTest. Error: Error: MissingSubscriptionRegistration. The subscription is not registered to use namespace 'Microsoft.CognitiveServices'. See…
Rejection for potential voice biometric vulnerabilities
I could not find any documentation regarding the following two cases for voice recognition in MS Azure: 1- if a recording of a previous enrollment is used for verification, is it rejected? 2- if a single recording of a previous verification is…
list of all phonemes used by pronounciation assessment service
Hello, I am looking for a list of all phonemes used by the pronunciation assessment service. Also, is there any word-phoneme mapping dictionary that the pronunciation service is using for checking the correctness? Best regards Rob
cognitive pronounciation assessment send file directly from S3 bucket
When sending audio data to pronunciation assessment service, is it possible to provide a link to a file stored in e.g. S3 bucket?
[Japanese] Does the model of azure speech-to-text is the same as that of teams' live captioning?
Hello. We are using teams and azure speech-to-text in Japanese. We think the performance of azure speech-to-text is better than that of teams' live captioning, because the former one could recognize more proper nouns such as kaggle. Does the model…
Questions About CNV(Custom Neural Voice) Quotas and Limits.
Hi I have few questions while reading CNV(Custom Neural Voice) quotas and limits. (link below) …
Question About Azure Custom Neural Voice Training Data
Hello. I have a question while using Azure's Custom Neural Voice. I wonder if the silence time in the front and back of the voice file of the training data used when training Custom Neural Voice affects the silence time in the front and back of the…
Azure Custome Voice & Viseme Event
Hello, I'd like to train my own audio resource by Azure Custom Voice. Before I get start it, I have a question about Is Custom Neural Voice support a Visemes too?
Azure Speech Service TTS FromEndpoint C#
Hello Now I'm using Azure Speech Service TTS by C#. And I also use Viseme Event. While I using it, I was curious about change configuration method SpeechConfig.FromSubscription("<my subscription key>","<my region>")…
speech to text (realtime)
I need help. I want to recognize real-time speech and see a list of predicted words. So, I want to apply a function called NBest to Python, but it doesn't work properly. I would appreciate it if someone could tell me the problem with the simple code…
Intent Rrecognition through JS won't record and recognize the intent
Hi, I am working on the Intent Recognition Quickstart from the following link https://video2.skills-academy.com/en-us/azure/cognitive-services/speech-service/get-started-intent-recognition?pivots=programming-language-javascript It was working fine on…
Speech Studio's Custom Keyword for Mandarin Advanced Model seems to not work as of August 27, 2021
Hi, I've been messing around with Speech Studio's Custom Keywords - Mandarin as the language for a few months. Advanced models for 2 words in Mandarin from my testing seems to not work at all. I have also tried a couple of 4 word phrases. I create…
Get facial pose events
Hello, When I get viseme events I can get the Viseme ID and Audio offset. Audio offset is the start time of each viseme. How do I know when the end time of each viseme.? thx.
Questions about Azure Speech APIs function.
I have used voice APIs with various functions and feel that Microsoft's Azure Speech API is the best. However, one question is, can you show several recognized results like the Google Speech API function? For example, I wonder if other words…