- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
hi
i'm looking for an API which can help me detect the voice presence in a conversation.
tks - hitesh
Link Copied
3 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi
Voice detection (VAD) is generally done as a small codec or as a component of the codec.
It exists in the majority of speech codecs,see ippSR examples (VAD example in Audio processing and voiced/unvoiced frame detection in Pitch Detection Example). Generally VAD algorithms are integrated into codecs but could be extracted from them. Ipp contain some functions to support general calculations while voice detecting:
Zero crossing calculation, periodicity, energy calculation (dotprod) etc
Most efficient way of VAD brings the apiG729EncodeVAD() function (no actual encoding, just only VAD).
Regards,
Vladimir
Vladimir
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Where can I find these ippSR examples? Online? Within the IPP documentation? Can you be specific? I have IPP 4.1 but can't find the samples. where is the G729 function you mentioned? Thanks!
Matt
Matt
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The IPP samples based on IPP version 4.1* including Speech Recognitions are downloadable via http://www.intel.com/cd/software/products/asmo-na/eng/perflib/ipp/219967.htm
As you may notice that we have more improved and expanded samples from latest 5.0 beta, you can try the latest samples offered in 5.0 beta. The IPP 5.0 based samples descriptions are located at here.
Hope it helps.
Thanks,
Ying S
Intel Corp.
Thanks,
Ying S
Intel Corp.
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page