Speech comparison

Hello, Im trying to make a VI that compares a speech input from a microphone to wav files in a folder. If the input speech matches any of the wav files in the folder it will output a specific text. I'm trying to implement this using Neural net but im stomped. HELP! Thanks

Hello,
Can you post the code you came up with and explain what you could do, what you couldn't do, etc...
If you go into Help > Find examples... > Search tab > search for "wav" you'll find "Recored Wav File.vi", maybe this will help you.
As to how to compare / match the WAV files... I'm sorry I will be of no help for that. Just use Shazaam
When my feet touch the ground each morning the devil thinks "bloody hell... He's up again!"

Similar Messages

Alphawork's Speech For Java Retired? Alternative to use ViaVoice?

After looking at comparisons of several different speech recognition engines, I would really like to use IBM's ViaVoice for a speech recognition engine. However, it appears Alphawork's Speech For Java has been retired. Why was this retired? What can I do as an alternative? Googling has not brought any answers for me. If I can't use this, I guess I'll just use Sphinx. The comparison I read reported that IBM's ViaVoice had a 53% accuracy in their tests, while Sphinx was only 38%.
http://www.voxforge.org/home/forums/message-boards/speech-recognition-engines/comparing-sphinx-ibms-via-voice-philips-speech-sdk-microsoft-win-xp-dragon-naturally-speaking

868518 wrote:
If there is some totally cross-platform standard for doing this, I would appreciate hearing about it.
ThanksBut there is no such thing as a "document created by Java". Documents are created by applications. Solutions for sharing data between applications is also solved at the application level, not through the programming language. Microsoft came up with OLE to be used in their Office suite mostly, you really don't need an over-complex solution like that.
So listen to Darryl: don't focus on a solution, what is that you want to functionally achieve?

Report for Comparison of Material Qty

Hi All,
I need to Develop an Interactive report for Comparison of Material Qty. ordered through Purchase requisition, ordered material through PO and corresponding Material Receipt report.
Can Someone Give a brief description about this & fields tcode & tables regarding this report.A sample code would be much appreciated.
Thanks & regards,
Ravi S

To get the material number combined with the PO text you will need the help of an ABAP programmer. The programmer can create a report for you using the function module READ_TEXT in the function group STXD. The tables to use are:
STXH - STXD SAPscript text file header
STXL - STXD SAPscript text file lines
The selection screen should have at least the following:
OBJECT - STXH-TDOBJECT
NAME - STXH-TDNAME
LANGUAGE - STXH-TDSPRAS
TEXTID - STXH-TDID
You find the information for these fields by going to the PO text entry screen and displaying the header information under Goto -> Header. For materials, the object is MATERIAL, the name is "material number", the language is "EN", and the text ID is BEST. You can use this program to get long text in lots of places like information records, purchase order texts, etc.
Hope this helps.

How can I convert an audio file (speech) into a text?

Hello everybody!
Can someone explain how I can convert a garageband file (voice speech) into a text? My Mac is a Mac OS X 10.5.8 version, so I don't have programs such as mountain Lion. I thought to use googlevoice. Is this option available? If yes, how can I use it?
Thanks.

Hello, I only find google voice available for Abdroid!?
http://www.ehow.com/info_10033225_google-voice-system-requirements-android.html
Some possibilitities, not sure if they have 10.5.8 compatble versions anymore...
http://atmac.org/speech-to-text-dictation-software-for-os-x
Some reviews of later Dragon Speak...
http://www.finetunedmac.com/forums/ubbthreads.php?ubb=showflat&Number=22962

How to do comparison in a loop.

Hi all,
TYPES: BEGIN OF ZROUTE,
         VBELN TYPE VBELN,
         ROUTE TYPE ROUTE,
        END OF ZROUTE.
DATA : IT_ZROUTE TYPE STANDARD TABLE OF ZROUTE,
         WA_ZROUTE TYPE ZROUTE.
      LOOP AT I_XVTTP_TAB INTO LW_XVTTP.
        WA_ZROUTE-VBELN = LW_XVTTP-VBELN.
        SELECT SINGLE ROUTE
                INTO WA_ZROUTE-ROUTE
                FROM LIKP
                WHERE VBELN = LW_XVTTP-VBELN
        APPEND WA_ZROUTE TO IT_ZROUTE.
     ENDLOOP.
results from IT_ZROUTE
vbeln    route
1111     A
2222     B
I have some problem in with the code below. I tried to collect vbeln and route into IT_ZROUTE.
However, after i've got the result, i want to do distiguish between the route.
If route A ne route B, then display an error messages.
My problem is, how do i compare the record by looping IT_ZROUTE? if i set into a temporary variable, the value will always change and i have prb in doing the comparison. eg:
loop it_zroute into wa_route.
   zroute = wa_route-route. "set into a variable
if zroute = wa_route-route
   "display error message
endif.
endloop.
Could anyone give me some tips to enhance my code? Really appreciate your help.

Hi SW,
You should never use SELECT statement inside LOOP statement as it will affect performance of the program. Use FOR ALL ENTRIES for the same.
TYPES: BEGIN OF ZROUTE,
VBELN TYPE VBELN,
ROUTE TYPE ROUTE,
END OF ZROUTE.
DATA : IT_ZROUTE TYPE STANDARD TABLE OF ZROUTE,
WA_ZROUTE TYPE ZROUTE.
************Addition STARTS***********
data : I_XVTTP_TAB_temp like I_XVTTP_TAB occurs 0 with header line.
data : begin of likp_itab occurs 0,
            vbeln like likp-vbeln,
             route like likp-route,
          end of likp_itab.
I_XVTTP_TAB_temp[] = I_XVTTP_TAB[].
sort I_XVTTP_TAB_temp by vbeln.
delete adjacent duplicates from I_XVTTP_TAB_temp comparing vebln.
select vbeln
          route
    into table likp_itab
   for all entries in I_XVTTP_TAB_temp
where vbeln eq I_XVTTP_TAB_temp-vbeln.
if sy-subrc eq 0.
sort likp_itab by vbeln.
endif.
************Addition ENDS***************
LOOP AT I_XVTTP_TAB INTO LW_XVTTP.
WA_ZROUTE-VBELN = LW_XVTTP-VBELN.
****************Not required
SELECT SINGLE ROUTE
INTO WA_ZROUTE-ROUTE
FROM LIKP
WHERE VBELN = LW_XVTTP-VBELN
****************Not required
read table likp_itab witj key vbeln = LW_XVTTP-VBELN binary search.
if sy-subrc eq 0.
WA_ZROUTE-ROUTE = likp_itab-route.
endif.
APPEND WA_ZROUTE TO IT_ZROUTE.
*********Add
clear wa_zroute.
*********Add
ENDLOOP.
Please explain the later part again I am not clear with requirement.
Regards,
Anil Salekar

Problems with string comparison using

I have a problem using the > and < comparison operators.
When the xsl:if test uses numeric values the comparison works OK. If the
test uses string values it always returns a false result.
The style sheet below shows an example (which should run against any
XML doc with a root element)
Note - the spurious
tags are just for debugging- I write the
output to an HTML page and IE happens to recognise them
even though the rest of the HTML tags are missing !!
<?xml version="1.0" ?>
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" >
<xsl:template match="/">
<xsl:for-each select="*">
Starting numeric test :
<xsl:if test="(1 < 2)">
In Test, ID= <xsl:value-of select="generate-id()"/>
</xsl:if>
Finished numeric test :
Starting alpha test :
<xsl:if test="('a' < 'b')">
In Test, ID= <xsl:value-of select="generate-id()"/>
</xsl:if>
Finished alpha test :
</xsl:for-each>
</xsl:template>
</xsl:stylesheet>
null

Having looked at the XPath spec I believe what I am trying to do (compare strings with gt and lt type tests) is not supported. The spec indicates that they can only be used for node sets or numerics. Presumably the processor is attempting to convert the values to numbers but evaluating them both as NaN (not a number). Can someone confirm this.
I find this restriction quite strange, is this a situation where an extension function is required ? If so can someone point me to some (Java) examples.
null

How to take back resources from speech engine

i make an application in swing in which i use jsapi text to speech which read and speak the selected file.
but when synthesizer starts speaking it takes all resources back from jframe hence buttons not worked till speech completed thats why i am unable to use stop button .
and if possible also give me detail how to read pdf's doc,.... files ..
Thanx

Sam_from_India wrote:
by freetts and jsapi i am reading files by io and spoken by jsapi and it worked . but when i select pdf or doc file java.io cant read doc or pdf normaly because these files are encoded hence unable to speak right ....There is no simple general method to extract the 'text' from all file types since most file types such as 'doc' files and 'pdf' files have markup that indicates how they should be formatted. For each different file type you will need to find a library that can read and interpret the file. PDF can be read using iText and 'doc' files can be read using Apache POI but in both there are limitations as to what they can accept.
P.S. I have used FreeTTS for one project. Works great except when the text contains abbreviations or slang.

Urgent : Help required for logical comparison of two 2GB files.

Large files need to be compared depending on Business logic. No byte to byte comparison to be done. It would require reference of data written at the start of the file at some other later part of the file too while comparing two files. File needs to be stored in memory while comparison is done. Kindly suggest some way out which would give best performance. Memory limitations are 256 MB RAM.

File needs to be stored in memory while comparison is done.
Memory limitations are 256 MB RAM.You have 4 GB of data. You have 256 MB of RAM to put it in. Obviously one of those two assumptions has to be changed. By the way, what is the XML connection for this question?

Text to Speech does not appear to be working in the new version of Pages

I have tried several ways to get the text to speech feature to work with the new version of Pages, but haven't yet had success. I use that feature in editing my articles alot, so I guess I'll stick with Pages 09 for now.
Anyone found a work around?

Nope, working as intended.
Pages 5 breaks accesibility completely.
If you're visually-impaired DO NOT UPDATE.

HT5449 speech to text capability on macbook pro

I have a macbook pro with 10.7.5 Is there any way I can get the dictation and speech capability of 10.8?

You can purchase:
http://shop.nuance.com/store/nuanceus/en_US/pd/ThemeID.20545600/productID.255083 500
http://www.amazon.com/Dragon-Dictate-3-0-Mac-Version/dp/B009348X7Q
You want version 3, Version 4 require ML or later

VTML-Tags for text-to-speech do not work in Captivate 6 - are they working in Cap. 7 again?

I had a hart time to find out, that the functionality was "forgotten" to be programmed in the version 6.
Together with Neospeech I worked long to make single voices work in full functionality and it cost additional licence fee... unfortunately the voices sound tinny so I cannot really use them...and due to different time zones it is hard to find the error together with Neospeech
Now I see that Captivate 7 is available.
Is there already qualified info if the vtml tags work again like they did in older versions?
Adobe Support hotline was NO HELP at all, very unfriendly... only idea was, that I should get the test version and find out myself, pretty impertinent.

Hi
You might already know this, but stating it here to rule out the simple failure cases.
I have had a similar problem in the past using VTML tags inside Captivate. I used to type the slidenotes in my favorite editor and then copy paste the text from there to the slidenotes panel of Captivate. Turns out that my editor was using Unicode and hence the entire text pasted into Captivate slidenotes became unicode text, including the VTML markers. Though the pasted text "looked" fine the markers were messed up (for example, the double quotes around the value attributes looked like double quotes but they were actually multibyte unicode sequences) and this confused Neospeech. The output audio would be funny (for example it would read "Less Than...V...T...M...L...") or NeoSpeech will crash taking down Captivate along with it.
The fix was quite simple. I started typing the slide notes from within Captivate slide notes panel and everything worked fine after that. Alternately I could type in my favorite editor (after making sure that it is operating in Plain text mode) and then copy paste work flow also worked fine.
Another common mistake (at least, I do that often) is to select the speech agent from the drop down at the top of the dialog and forgetting to choose the speech agents for individual slide notes, which may still be referring to a non-neo-speech agent which does not understand the VTML tags.
No other software tool was required like the German Adobe Support team may have mentioned. I am using Captivate 7.
Cheers
Siva

Features comparison of SharePoint Foundation 2010 & Office 365

Hi,
I there any documentation/chart or table comparison of features between Office 365 and SharePoint Foundation 2010?
I can only search comparison between office 365 and SP Foundation 2013.
Thanks!

See http://technet.microsoft.com/en-us/library/sharepoint-online-service-description.aspx
Towards the bottom it has the on-prem feature sets, but has all of the online and onprem feature sets listed on this page.
Trevor Seward
Follow or contact me at...
&nbsp&nbsp
This post is my own opinion and does not necessarily reflect the opinion or view of Microsoft, its employees, or other MVPs.

Using inline tags in text to speech to alter pronunciation and other things

We're converting a weekly paper newspaper into speech, then to iTunes as mp3s to cut a CD or stick via Garage Band for a number of sight-impaired subscribers.
We've been using TextEdit to edit the text that we receive as pdfs (or copy/paste from the newspaper website) to make it suitable for listeners and of course shorter. Problem is, that some words are mispronounced, and we sometimes need longer pauses between paragraphs.
We get around the mispronunciation by mis-spelling words. That has been working for us, although Voice Over has exactly what we want from the pronuniation point of view, but does not work with the application we're using.
We've also worked out how to use some inline tags, such as [[slnc 5000]] but examples such as [[pron sym]]="h eh 1 l ow & w er 1 l d "[[/]] simply don't work. What am I missing? Do I need to go to a specific set of xml or other tags or a standard set of tags that always work with Apple's tts engine?
Look forward to a positive result.

absolutely nothing bad will happen if you use a keyboard shortcut that's designated for something else. if you don't know it it means you don't use it so what's the problem? just use anything you like. use commandoptionL. that's not used for anything.

How can I make rectangular speech bubbles that adapt to the text inside them without the "arrow" that points towards where the bubble is coming from getting changed?

I have to make lots of speech bubbles (150+) that all have texts inside them which differ in length. I want the speech bubbles to look the same in terms of style, but I need different sizes of course for each text. This means that the rectangular part of the speech bubble should adapt in length and width to the text inside it, while the "arrow" pointing towards where the bubble is coming from (e.g. the person who speaks) should stay the same on every bubble. So is there a way or a workaround to make such "adapting" speech bubbles?
I appreciate any kinds of help
Thanks in advance!

Here's another way I found:
1. Draw a speech bubble. Mine is a rectangle with rounded corners and a triangular pointer added with Pathfinder > Add
2. Drag out a frame the same size as the speech bubble. Select the speech bubble and Copy; then select the empty frame and choose Edit > Paste Into...
3. Alt-Drag the frame with the pasted speech bubble to make a copy, then crop one copy to leave only the top of the bubble showing, and crop the other copy to leave only the bottom.
4. Drag out a text frame and insert a table consisting of 1 column, 3 rows. Set the text frame to Autosize > Height Only.
5. Set the stroke/fill of the top and bottom rows to none, and style the middle row to match the speech bubble, (in my case a white fill and 2pt stroke; left and right).
6. Anchor (paste) a copy of the speech bubble top in the top table row, and a copy of the speech bubble bottom in the bottom row.
Getting the 3 parts to match up with is where you just have to work on it until you get it right. Use the positioning tools in Anchored Object options and the column width setting in Cell options to line everything up.
Enter your text in the middle row. (Hey, look at that...a valid application of Comic Sans!) With the Cell Height set to an "At Least" setting, the cell will expand to fit whatever text you enter, pushing the the bottom row down, with the text frame auto-sizing to keep everything in play...

The Comparison of IIS on Windows Server 2012 R2 and Websphere application Server on R6 or AS400

Customer is looking for the internet application solution, and they would like to know the difference/ comparison of IIS on Windows Server and WAS on Linux. I know it's hard to answer, but is there any data/document/information so that we could convince
customer to use IIS instead of WAS on R6/AS400?

Hi,
I could not say which one is better.
The advantage of IIS, you could refer to:
http://www.microsoft.com/web/platform/server.aspx
Similar thread has been discussed:
Windows/.NET/ASP.NET/IIS/SQL Server vs. Linux/WebSphere/Java/Apache/Oracle information
https://social.msdn.microsoft.com/Forums/en-US/9d3b975d-42cb-48fc-94c4-a0394d9f34e6/windowsnetaspnetiissql-server-vs-linuxwebspherejavaapacheoracle-information?forum=architecturegeneral
Meanwhile, i think you could ask in IIS forums:
http://forums.iis.net/
Regards.
Please remember to mark the replies as answers if they help and unmark them if they provide no help. If you have feedback for TechNet Support, contact [email protected]

Speech comparison

Similar Messages

Maybe you are looking for