guys, are there some software tools implementing basic GSM vocoders?
For example, I need the following functionality:
feed voice traffic (e.g. as microphone audio traffic with high bitrate) to GSM vocoder input;
get GSM vocoder output as encoded speech with lower bitrate.
Related
I need to integrate Speech To Text (STT) service with IP telephony. STT service support just 5 particular input formats of audio (MuLaw/ALaw/Linear16/RawOpus/MP3) and 10 sample rates (8/11/12/16/22/24/32/44/48/96k).
How to check which format and sample rate does my VoIP provider use?
Can I do that with linphone(linphone-cli) or pyVOIP or SIP.js or pjsip?
I will be grateful for code or commands examples
Your provider doesn't use anything by itself. The question is what the devices you will call will support.
Iam using Unity SDK provided for IBM Watson services. I try to use 'ExampleStreaming.cs' sample provided for speech to text recognition. I test the app in unity editor.
This sample uses Microphone as audio input and gets results for voice input from the user. However, when I use microphone as input, the transcribed results are far from being correct. When I say "Create a black box", the results are inappropriate, with the word results being completely irrelevant to input.
When I use pre-recorded voice clips, the output is perfect.
Does the service perform incorrectly for Indian accent?.
What is the reason for poor microphone input recognition?
The docs say:
"In general, the service is sensitive to background noise. For instance, engine noise, working devices, street noise, and talking can significantly reduce accuracy. In addition, the microphones that are typically installed on mobile devices and tablets are often inadequate. The service performs best when professional microphones are used to capture audio with better quality."
I use Logitech headset mic as input source.
Satish,
Try to "clean up" the audio as best you can - by limiting background noise. Also be aware that you can use one of two different processing models - one for broadband and one for narrowband. Try them both, and see which is most appropriate for your input device.
In addition, you can find that the underlying speech model does not handle all of the domain specific terms that you might be looking for. In these cases you can customize and expand the speech model, as explained in the documentation on Using Custom Language Models (https://console.bluemix.net/docs/services/speech-to-text/custom.html#custom). While this is a bit more involved, it can often make a huge difference in accuracy and overall usability.
Is it possible output both live audio and MIDI RTP data from Bluetooth device of iPhone? Looking to leverage the Core MIDI library. Crucial is the ability to fire off both sources simultaneously with no latency.
Many thanks........
Hello all i use windows encoder to stream video online and have a server that i use to broadcast this stream. i am trying to make an app that streams video to the iPhone/iPad using a unique link. i have seen apps out that stream their own DVR cameras so there must be a type of converter or encoder to use. any suggestions?
The short answer is no, not at this time. The iPhone/iPad/iPod Touch work natively with the Apple HTTP Adaptive segmented streaming protocols. MMS (Windows Media) streams are not compatible with "i" devices and will not play. You will need to look into encoding your video with this other format. Check out the Apple specs for a full description of the protocol. Future versions of Windows Media Services (4.0) are claiming that they will support the Apple protocols but this is only a preview/beta at this time and may not truly support the Apple specs.
If your trying to do on-demand iPhone video, you can utilize a service such as Encoding.com to pre-encode your files in the adaptive segmented format for your users to view. For live encoding, Telestream has a product called Wirecast which can encode in a h.264 Apple approved baseline format which can be sent to a service such as Akamai, Multicast Media, or Wowza Server for distribution to your clients.
I need to develop an embedded audio streaming server.
Requirements:
Voice quality or better
Intended for low power wifi transmission
Broad support in existing software and devices (ie, windows media player, quicktime, vlc, iPhone, Android, etc).
Royalty/patent free, or cheap to license
Preferences:
Low overhead TCP/IP based streaming protocol
Voice grade codec (easy to implement in software, no DSP, 32bit CPU if needed)
Would be nice if it supported HTML5 browsers, but is there any codec (such as raw) that is supported by the latest browsers that is lower overhead than MP3?
Therefore:
What are the relevant streaming protocols I should be looking at?
What are the relevant codecs I should be looking at?
What transport streams should I be looking at?
What am I missing, or where else should I be looking for this type of need?
The easiest route would be to wrap the iPhone 3G S' hardware accelerated AAC codec in some sort of standard network stream; I think it's royalty free. For broad support, your best option is MP3 over HTTP shoutcast-style (not royalty free).