cmusphinx

问题 Actually hello world demo example has a few words but I want to add more words in it. Its seems possible to do either two ways. 1. Update the hello.gram file 2. create my own gram file. But the issue is that I'm unable to do either way. Can you please help me in it. Thanks for your time. Sorry for bad english. Here is my hello.gram file which I updated. I updated no other file. Please help me in this sort. hello.gram file #JSGF V1.0; /** * JSGF Grammar for Hello World example */ grammar hello

问题 At run time we are populating a list of files and folders. I want to add that list in the Gram file. I really have no idea how to change the gram file and load it again. I have gone through sphinx JSGF but because the lack of time I am not able to read it completely. I am using sphinx4-1.0beta6 version. 回答1: If you want to change in your gram file then you need to add them in dictionary file acoustic model. Create a txt file “ words.txt ”, Write all the names of cities and states in it and

问题 i'm using CMU sphinx to recognize alphabet letters, but i'm noticing very low accuracy.( <=20%). for example : when I spelling letters: A-P-P-L-E, it come out A B B L E. the accuracy is too low to be useful. I hope don't have to implement it like some posts mentioned, using "alpha""beta" etc. for improving the recognition rates. the dict file and lm file in generate in online lmtools BTW: the accuracy rate is above 80% when i limit the dict and speak to microphone with words . so does anyone

问题 I have an idea for an app that may need CMU Sphinx, is it available via maven, or do I need to add it by hand? 回答1: Update: CMUSphinx is going to be available in sonatype in a week or so. The maven support has already been committed into sphinx4 trunk. 回答2: You can check from http://cmusphinx.sourceforge.net/wiki/tutorialsphinx4: Overview Sphinx-4 is a pure Java speech recognition library. It's very flexible in its configuration, and in order to carry out speech recognition jobs quite a lot

问题 I am trying to extract the start and end timestamps of each segment using pocketsphinx. The code below works for extracting the word token. How can I access the timestamps? I've tried looking at the documentation here http://cmusphinx.sourceforge.net/doc/pocketsphinx/index.html but could not find the method #!/usr/bin/env python import os import sphinxbase as sb import pocketsphinx as ps MODELDIR = 'deps/pocketsphinx/model' DATADIR = 'deps/pocketsphinx/test/data' # Create a decoder with

问题 Has anyone used the Sphinx speech recognition stack to build IVR applications? I am looking for open source alternatives to the expensive and somewhat limiting choices from MSFT and others. I have not been able to find a comprehensive package that ties open source speech/voip applications together. 回答1: Last I looked at Sphinx, it had issues with 8khz audio which resulted in really poor performance. There's not a lot of people talking about successful deployments of Sphinx in real

问题 I'm trying to follow this tutorial, and it crashes upon startup after having lots of problems with the dictionary and models, such as. The dictionary is missing a phonetic transcription for the word 'humphrey' and Dec 18, 2014 1:14:50 PM edu.cmu.sphinx.linguist.lextree.HMMTree addPronunciation SEVERE: Missing HMM for unit T with lc=N rc=EH1 13:14:50.601 SEVERE lexTreeLinguist Bad HMM Unit: EH1 I loaded this dictionary and got the language and acoustic models from their SourceForge page It

问题 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 " + "! level name=wavelevel interval=100000000 " + // level interval is in nanoseconds "! wavenc " + "! filesink location=audioz.wav" ); It works fine except that the streaming stops when there is no voice comming in the source. I want to recording to continue independently of the VAD, so I

问题 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 directory `/home/root/Pocketsphinx/sphinxbase-0.8/src' Making all in libsphinxbase make[2]: Entering directory `/home/root/Pocketsphinx/sphinxbase-0.8/src/libsphinxbase' Making all in util make[3]: Entering directory `/home/root/Pocketsphinx/sphinxbase-0

问题 Trying edu.cmu.sphinx.pocketsphinx with processRaw to detect silence. Using the following config: en-us.lm.bin language model en-us-ptm acoustic model cmudict-en-us.dict dictionary also setting remove_noise to True and samprate to 8000 I want to do a Ngram Search. When the While loop calling processRaw finishes I call both hypothesis.getHypstr() and decoder.getInSpeech() Why does getHypstr returns empty but getInSpeech returns True while actually there is no speech in the input argument given