Stack Overflow
Stack Overflow

Questions tagged [cmusphinx]

An open-source toolkit for speech recognition. Includes speech recognizers Sphinx 2-4, PocketSphinx and a set of tools to supplement the recognizers.

CMU Sphinx is a group of speech recognition systems developed at Carnegie Mellon University.

Links:

682 questions
0
votes
0 answers

PocketSphinx Recording IllegalStateException Error for AudioRecord object

On some devices (none of the actual test devices), I get a force close when I start PocketSphinx recognition, the crash report is as follows (note it was previously obfuscated): java.lang.IllegalStateException: startRecording() called on an…
Ryan S
  • 4,549
  • 2
  • 21
  • 33
0
votes
1 answer

Error while running JSGFDemo from Sphinx4

I'm trying to run JSGFDemo from sphinx4 demos. I followed these steps from terminal: cd /Users/username/sphinx4-1.0beta6 java -mx200m -jar bin/JSGFDemo.jar But I got this error: Exception in thread "main" java.lang.ExceptionInInitializerError at…
Evanescence
  • 729
  • 1
  • 10
  • 25
0
votes
1 answer

Which language model to use for dictation

I intend to use the sphinx4 in dictation mode but I have a question about the language model. My application will have a very large vocabulary, ie, it can use all the English words and I do not know which will be the phrases that will be said. So…
user3322314
  • 3
  • 1
0
votes
1 answer

How to accept more sentences by sphinx4

I'm using Sphinx4 version 4-1.0beta6 over my mac osx 10.9.1 through the terminal. I'm still new in this SR application. I've already run HelloWrold example and added some new words to the gram file and it worked. Now, I'd like to use rules or…
Evanescence
  • 729
  • 1
  • 10
  • 25
0
votes
1 answer

Recognition of the file without grammar constrains

As the gram file that is used to convert audio to text, we have only a limited number of words that can be recognized. is there any way to transcribe any audio to text. Can we enhance the gram file to contain all the English words so that any of the…
Vishwanath
  • 149
  • 2
  • 14
0
votes
1 answer

Grammar with dictation using Sphinx-4

I'm using Sphinx-4 to convert voice to text, but I need that the application recognizes a grammar and then a sequence of words dictated. For example, having the following grammar: public = (Good morning | Hello); If I say "Hello" and then…
user3267555
  • 1
  • 1
0
votes
1 answer

How do I config sphinx4 for general purpose recognition?

I want to use sphinx4 for general purpose voice recognition, e.g. you tell the application something and it prints what you've said. However when I walk through the examples it's all about recognising a very small amount of vocabulary. Is there any…
tactoth
  • 897
  • 1
  • 12
  • 24
0
votes
0 answers

How to add package in such a way that program does'nt crash

What happens is that if i add all the libraries up along with helloworld.jar, it works. But as soon as i add a new class and make it add the code: package edu.cmu.sphinx.demo.helloworld; and then there is a error on it so i click it and click on…
Daksh Shah
  • 2,997
  • 6
  • 37
  • 71
0
votes
0 answers

pocketsphinx recognizes partial sentences

I am using pocketsphinx to recognize a series of commands, but I am getting partial sentences from time to time. For example, my grammar is similar to this: #JSGF V1.0 ISO8859-1 es; grammar fsg.prueba; public = (<1>|<2>|<3>|<4>); <1>=HELLO…
vguzmanp
  • 785
  • 1
  • 10
  • 31
0
votes
1 answer

Can I put 2 or 3 or event more sentence in reference text that will be used to generate the language model

I have read some tutorial on creating lm. I was a little confuse about weather.txt. I have sentences like this: (putting silence mark at the start and end of the sentence.) OK IS THERE A COMPUTER IN MY ROOM can I put two…
no7dw
  • 505
  • 5
  • 13
0
votes
1 answer

Beaglebone: gcc include path error while trying to build using 'make'

I am trying to build cmu pocketsphinx on my beaglebone black for speech recognition. I have downloaded the source code for sphinxbase and ran ./configure. Now, when I run 'make' I get the following errors: Making all in src make[1]: Entering…
mdzahedhossain
  • 125
  • 1
  • 14
0
votes
1 answer

How many hours is needed for training the acoustic model

I want to build a English acoustic model for children under 14 in China, with about 800 words in vocabulary, using cmusphinx. I did some research that some commercial voice engine take thousands of hours of voice record to train their acoustic…
no7dw
  • 505
  • 5
  • 13
0
votes
1 answer

gstreamer pipeline with VADER element stalls on PAUSE when used with a tee

I have this pipeline that uses pocketsphinx's VAD element : Gst.parse_launch( "pulsesrc device=\"alsa_input.usb-046d_08c9_674634A4-02-U0x46d0x8c9.analog-mono\" " + "! vader name=vad auto-threshold=true " + …
Max L.
  • 9,774
  • 15
  • 56
  • 86
0
votes
0 answers

Sphinix GUI trainer Failed to compile

i am trying to create ASR system for my native language called amharic and my plan is to make an aquastic model without toomuch effort. for that i thought i could use ASTRA(Advanced Sphinix Trainer ) which is made using QT. but the thing is there is…
Serak Shiferaw
  • 993
  • 2
  • 11
  • 32
0
votes
1 answer

Sphinx 4 Transcription Time Index

How do I get time index (or frame number) in Sphinx 4 when I set it to transcribe an audio file? The code I'm using looks like this: audioURL = ... AudioFileDataSource dataSource = (AudioFileDataSource)…
Bill
  • 1,271
  • 1
  • 10
  • 13
1 2 3
…
45 46