Sir, I have trained the models by taking large number of sentences. Using those models I have obtained the boundaries using sphinx3_align.
Then I tried to do forced alignment at paragraph level using those models only.
The transcription will look like this
YOU WISHED TO KNOW ALL ABOUT MY GRANDFATHER WELL HE IS NEARLY NINETY THREE YEARS OLD HE DRESSES HIMSELF IN AN ANCIENT BLACK FROCK COAT USUALLY MINUS SEVERAL BUTTONS YET HE STILL THINKS AS SWIFTLY AS EVER A LONG FLOWING BEARD CLINGS TO HIS CHIN GIVING THOSE WHO OBSERVE HIM A PRONOUNCED FEELING OF THE UTMOST RESPECT WHEN HE SPEAKS HIS VOICE IS JUST A BIT CRACKED AND QUIVERS A TRIFLE TWICE EACH DAY HE PLAYS SKILLFULLY AND WITH ZEST UPON OUR SMALL ORGAN EXCEPT IN THE WINTER WHEN THE OOZE OR SNOW OR ICE PREVENTS HE SLOWLY TAKES A SHORT WALK IN THE OPEN AIR EACH DAY WE HAVE OFTEN URGED HIM TO WALK MORE AND SMOKE LESS BUT HE ALWAYS ANSWERS BANANA OIL GRANDFATHER LIKES TO BE MODERN IN HIS LANGUAGE (M05-SEASON1-0105)
From sphinx3_align I am getting the following error
INFO:feat.c(1205):Atdirectory/home/sitecsp/AUTOMATIC_REPETITION/an4/featINFO:feat.c(1022):Readingmfcfile:'/home/sitecsp/AUTOMATIC_REPETITION/an4/feat/an4test_clstk/M05/SEASON1/M05-SEASON1-0105.mfc'[0..-1]ERROR:"feat.c",line1112:/home/sitecsp/AUTOMATIC_REPETITION/an4/feat/an4test_clstk/M05/SEASON1/M05-SEASON1-0105.mfc:Maximumoutputsize(15006frames)<actual#frames(17014)ERROR:"main_align.c",line998:UttM05-SEASON1-0105:Inputfileread(an4test_clstk/M05/SEASON1/M05-SEASON1-0105) with dir (/home/sitecsp/AUTOMATIC_REPETITION/an4/feat)andextension(.mfc)failedINFO:corpus.c(661):M05-SEASON1-0105:0.0secCPU,0.0secClk;TOT:23.7secCPU,23.9secClk
Please help me. Thanks in advance.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Thanks for your reply. Is there is any other aligner that supports long file. I have a wavfile with max duration of 2.5 minutes.
Is there any option in the same aligner that process a long file.
Please help me
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Can I segment the speech signal into 2 parts so that it should not exceed the length and give as input to sphinx3_ align. Sir, is this a right way of doing.
Thank you.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Sir, I have trained the models by taking large number of sentences. Using those models I have obtained the boundaries using sphinx3_align.
Then I tried to do forced alignment at paragraph level using those models only.
The transcription will look like this
YOU WISHED TO KNOW ALL ABOUT MY GRANDFATHER WELL HE IS NEARLY NINETY THREE YEARS OLD HE DRESSES HIMSELF IN AN ANCIENT BLACK FROCK COAT USUALLY MINUS SEVERAL BUTTONS YET HE STILL THINKS AS SWIFTLY AS EVER A LONG FLOWING BEARD CLINGS TO HIS CHIN GIVING THOSE WHO OBSERVE HIM A PRONOUNCED FEELING OF THE UTMOST RESPECT WHEN HE SPEAKS HIS VOICE IS JUST A BIT CRACKED AND QUIVERS A TRIFLE TWICE EACH DAY HE PLAYS SKILLFULLY AND WITH ZEST UPON OUR SMALL ORGAN EXCEPT IN THE WINTER WHEN THE OOZE OR SNOW OR ICE PREVENTS HE SLOWLY TAKES A SHORT WALK IN THE OPEN AIR EACH DAY WE HAVE OFTEN URGED HIM TO WALK MORE AND SMOKE LESS BUT HE ALWAYS ANSWERS BANANA OIL GRANDFATHER LIKES TO BE MODERN IN HIS LANGUAGE (M05-SEASON1-0105)
From sphinx3_align I am getting the following error
Please help me. Thanks in advance.
Sphinx3_align does not support such long files, this is what message tells you.
Thanks for your reply. Is there is any other aligner that supports long file. I have a wavfile with max duration of 2.5 minutes.
Is there any option in the same aligner that process a long file.
Please help me
Can I segment the speech signal into 2 parts so that it should not exceed the length and give as input to sphinx3_ align. Sir, is this a right way of doing.
Thank you.
We have sphinx4 aligner for cases like this one:
http://cmusphinx.sourceforge.net/2014/07/long-audio-aligner-landed-in-trunk/
Ok, sir I will follow the tutorial thanks for your quick reply