Speech Recognition: Learn Digital Signal Processing

  • Thread starter Thread starter CylonMath
  • Start date Start date
Click For Summary
To develop a speech recognition software for PC, foundational knowledge in Digital Signal Processing (DSP) is essential, particularly in sound data processing techniques. Familiarity with Fourier series and transforms is beneficial. Understanding the complexities of speech recognition systems is crucial, as highlighted in resources like the Citizendium overview. Existing software options, such as Dragon NaturallySpeaking and Mac Speech, are noted for their effectiveness, though they require substantial system resources. Exploring these established tools can provide insights and save time in the development process.
CylonMath
Messages
34
Reaction score
0
Hello , I want to do a small Speech Recognition Software for my pc , to allow me use my voice to start some programs and execute some commands on shell ( I know there are others but i want to do in on the educational side)

What subjects i should learn first ? I haven't taken Digital Signal Processing courses yet, however i have knowledge in Fourier series and transforms. What should i know to process sound data ?

Can you describe briefly , thanks !
 
Computer science news on Phys.org
Thank you , that explains briefly.
 
As an FYI Dragon Natural Speaking is favored by the Doc and Attorneys I support. It is a big resource hog so a beefy PC is recommended.

http://www.nuance.com/naturallyspeaking/

I use Mac Speech on the OS X as well. It is impressive. It is built upon Dragon's engine.
http://www.macspeech.com/

I know you wanted to write something, but these might save you some time.
 
Thread 'ChatGPT Examples, Good and Bad'

Thread 'ChatGPT Examples, Good and Bad'

I've been experimenting with ChatGPT. Some results are good, some very very bad. I think examples can help expose the properties of this AI. Maybe you can post some of your favorite examples and tell us what they reveal about the properties of this AI. (I had problems with copy/paste of text and formatting, so I'm posting my examples as screen shots. That is a promising start. :smile: But then I provided values V=1, R1=1, R2=2, R3=3 and asked for the value of I. At first, it said...
View full post »

Similar threads

How were the fundamental improvements in Voice Recognition achieved?
  • · Replies 12 ·
Replies
12
Views
2K
Digital signal processing and the z-transform
  • · Replies 2 ·
Replies
2
Views
2K
What Are Some Recommended Books for Learning Speech Analysis and Recognition?
  • · Replies 1 ·
Replies
1
Views
4K
Restarting GNOME shell when it has frozen, without killing applications
  • · Replies 3 ·
Replies
3
Views
11K
Deep Learning for Image Recognition in Astrophysics
  • · Replies 3 ·
Replies
3
Views
2K
Losing Wifi hotspot when connecting to signal
  • · Replies 43 ·
2
Replies
43
Views
5K
Modern Digital Audio: Understanding Dither and Oversampling in Hi-Res Age
  • · Replies 17 ·
Replies
17
Views
5K
Undergrad Making Sense of Notation Confusion in Statistical Digital Signal Processing
  • · Replies 6 ·
Replies
6
Views
2K
Programming style in R - to array-process or not?
  • · Replies 2 ·
Replies
2
Views
1K
Baseband Signal Processing and Digital to Analog Converters
  • · Replies 2 ·
Replies
2
Views
2K