Questions tagged [sphinx4]

Sphinx-4 is a part of CMUSphinx Speech Recognition Toolkit. It's a flexible large and small vocabulary speech decoder written in Java and licensed under BSD license.

This tag is about Sphinx-4, a speech recognition decoder. Speech recognition is fastly growing domain and it's quite complex by its nature. The development of the speech recognition application requires understanding of the speech recognition specifics - a probabilistic nature of the results, the need for throughout testing, the specifics of the voice user interface design, the accuracy/speed balance.

The main concept you need to be aware about are acoustic model used to capture the sounds of the language, the language model used to capture the vocabulary and the dictionary which maps from words to sounds. The use of Sphinx-4 in your application is often straightforward but you need to be more careful than usually to get everything in place.

To learn more about CMUSphinx and Sphinx-4 visit CMUSphinx page

https://cmusphinx.github.io/wiki/

Read the tutorial

https://cmusphinx.github.io/wiki/tutorial/

255 questions
0
votes
1 answer

How to mix noise to "raw" file (AN4 database)

I am doing a research in noise reduction. Could anyone tell me how to mix a noise file with an audio file? I am working with the AN4 database, so they are all in "raw" format. Thanks in advance.
Thanh Bui
  • 405
  • 2
  • 5
  • 14
0
votes
1 answer

mp3 recognition using Sphinx 4

Can we use mp3 files for the voice recognition process without using wav files? or can we generate a wav file from a mp3 and then do the voice recognition without a serious impact on the accuracy? The problem is I need to minimize the load…
SDK
  • 175
  • 1
  • 15
0
votes
1 answer

recognizing all english words using sphinx4

I have a problem in recognizing all english words using sphinx4. I added all the english words starting with letter 'A' to my grammar file in java and tried to run it. First time it gave me the error of java heap space which i initially kept…
Abubakkar
  • 15,488
  • 8
  • 55
  • 83
0
votes
1 answer

using htk for non-digit recognizing

I have been trying to use HTk coupled with sphinx4 for a speech recognition application. I am providing my input as a wav file and i am using the sphinx provided "Transcriber demo' and the 'Lattice Demo" however the output was pretty much…
Raveesh Sharma
  • 1,486
  • 5
  • 21
  • 38
0
votes
0 answers

Impossible to pip install pysphinx

I am trying to use Pysphynx to run the following speech-to-text transcription code. It seems that there is just no way to install pysphinx, I get the standard error message: ERROR: Could not find a version that satisfies the requirement pysphynx…
Julien
  • 1
0
votes
1 answer

How to convert voice to text?

I am trying to converting my wav file to text file using sphinx4. Is it possible to recognize the word which is not include in grammar file?
RAAAAM
  • 3,378
  • 19
  • 59
  • 108
0
votes
1 answer

Debugging with jdb

Trying to figure out my way around Sphinx 4 (the CMU speech recognition engine in Java), I tried to use a demo included with the distribution by altering it to what I wanted it to do (the name of the demo is Aligner). I am running into problems and…
Sriram
  • 10,298
  • 21
  • 83
  • 136
0
votes
0 answers

SimpleAudioIndexer. Generating time-aligned text tags from audio file gives an error: ERROR: "cmd_ln.c", line 942: Unknown argument: -alignctl

I used the code below to generate time aligned text file from audio file. For that purpose, I installed SimpleAudioIndexer library. Also, I installed the required libraries by following this guide at…
hbtousa
  • 19
  • 4
0
votes
1 answer

How could I change the time before the speech result is closed CMUSphinx4

I want to change the time before the speechresult is closed. For example, If I say "Hello", and then wait a second before saying "Hi", they will be 2 separate speech results. If I say one right after the other, it works fine. I want sphinx to not…
Delected
  • 41
  • 4
0
votes
1 answer

sphinxtrain - Configuration not defined

I am trying to train an acoustic model for CMUSphinx following the tutorial here. So when i am training with the command sphinxtrain run, I am getting the following problems: Sphinxtrain path: /usr/local/lib/sphinxtrain Sphinxtrain binaries path:…
Ridwan
  • 214
  • 4
  • 17
0
votes
0 answers

How to import jar files in NetBeans

I am trying to build a very basic voice recognition application via a tutorial. I need to add sphinx4-core.jar and sphinx4-data.jar. I added them into my library and am attempting to import them into my code and I get a "package edu.cmu.sphinx.api…
0
votes
0 answers

Sentences Recognition Using CMU Sphinx

enter image description hereI am a researcher, and I am making speech recognition system using CMU Sphinx. I have succesfully trained words of Sindhi Language with very low accuracy. Now I wanted to train complete sentences. I was Wondering how to…
0
votes
0 answers

How to only detect keywords with continuous recognition for Sphinx4 in Java desktop application?

I am new to Sphinx and I have read about the various examples used across the multiple programming languages that allows for continuous voice recognition. I am trying to figure out the best way to do "keyword spotting" using Sphinx4 (5prealpha) with…
steven
  • 508
  • 1
  • 8
  • 23
0
votes
1 answer

Implementation of a dictation system using Sphinx4 and Python

I want to develop a dictation system using Sphinx4. After some search, I realize that the language that it's better to use is Java. Can I combine Sphinx4 with Python? I prefer Python because I want to enhance my system by adding neural network…
0
votes
1 answer

C# program using a sphinx4 .jar converted to .dll fails

When I try to instantiate the LiveSpeechRecognizer, it throws an error which gives the following stack trace: Exception thrown: 'edu.cmu.sphinx.util.props.PropertyException' in VoiceRecognition.dll at…
Astrolamb
  • 171
  • 12