Stack Overflow
Stack Overflow

Questions tagged [kaldi]

Kaldi speech recognition toolkit

Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.

113 questions
1
vote
1 answer

Speaker segmentation using Kaldi's x-vector approach

I'm using kaldi for asr and now I want to do speaker segmentation using Kaldi's x-vector approach. They are providing some example segmentation scripts at https://github.com/kaldi-asr/kaldi/tree/master/egs/sre16/v2 .They also provide a basic…
humble_wolf
  • 1,497
  • 19
  • 26
1
vote
1 answer

sclite (SCTK) `make check` faliure, C++/perl/Cygwin, Safe to use Perl4 stuff?

I am currently trying to install NIST's sclite, which is part of SCTK 2.4.0 (github or newer version). I am attempting the install on Cygwin in bash. The installation is done using make. I have gotten past the make configure and make all parts of…
bballdave025
  • 1,347
  • 1
  • 15
  • 28
1
vote
0 answers

Error in getting feature dimension on Kaldi for Voice recognition?

I have done 'Kaldi for dummies' example for Voice recognition. But I am getting the following error. Anyone knows how to fix it? error message showing while running Kaldi for dummies
Geo George
  • 31
  • 1
  • 4
1
vote
2 answers

How to setup Kaldi on Mac?

I have gone through the official documentation of kaldi, it is very hard to understand. can anyone suggest me a good tutorial which discribes how to run kaldi on mac??
Geo George
  • 31
  • 1
  • 4
1
vote
1 answer

cudaError_t 1 : "__global__ function call is not configured" returned from 'cublasCreate(&handle_)'

I run ASR experiment using Kaldi on SGE cluster consisting of two workstation with TITAN XP. And randomly I meet the following problem: ERROR (nnet3-train[5.2.62~4-a2342]:FinalizeActiveGpu():cu-device.cc:217) cudaError_t 1 : "__global__ function…
haibing cao
  • 11
  • 2
1
vote
1 answer

Kaldi librispeech data preparation error

I'm trying to do ASR system. Im using kaldi manual and librispeech corpus. In data preparation step i get this error utils/data/get_utt2dur.sh: segments file does not exist so getting durations from wave files utils/data/get_utt2dur.sh: could not…
Eclipser
  • 49
  • 3
1
vote
1 answer

Aligning class labels to data point on a waveform plot

I am currently trying to align extracted target values to a waveform plot. the target values, extracted are phoneme classes determining whether the word being uttered is (yes, no, silence). I've been trying to properly align the target values with…
Lamda
  • 914
  • 3
  • 13
  • 39
1
vote
1 answer

Kaldi feature dimension error

I run the kaldi tutorial for dummies and i get this error "error getting feature dimension". Can anybody help? Thank you for your time!
Kosta
  • 31
  • 3
1
vote
1 answer

Doing phoneme recognition given different sized audio files?

I am currently working on doing phoneme recognition with cnn. My dataset is labeled, but I am bit unsure how i ensure that the length of feature vector also will be according to the length of the audio file. My input to the CNN is currently a…
J.Down
  • 700
  • 1
  • 9
  • 32
1
vote
1 answer

Extract MFCC coefficient without the log?

I am currently trying to replicate the works of a paper, in which they train a cnn using MFCC features without the DCT performed at the end. It is basically the log of the energies of the filter banks. I know that kaldi can compute the MFCC…
J.Down
  • 700
  • 1
  • 9
  • 32
1
vote
4 answers

Kaldi toolkit Installation Error on Ubuntu 16.04

Hi I am trying to install Kaldi toolkit for speech recognition on Ubuntu 16.04. I have followed instructions in INSTALL file. (1) go to tools/ and follow INSTALL instructions there. Followed procedure in INSTALL file in tools and got following…
Srinivas
  • 176
  • 2
  • 12
1
vote
1 answer

Unable to extract delta and delta delta power spectrum computation

I am currently trying to extract the delta + delta-delta using add-deltas binary file provided by kaldi. But for some reason i am not able to extract it. I usually extract power spectrum using the make_spectrum.sh script. I modified it a bit to…
Loser
  • 67
  • 8
0
votes
0 answers

Adapting a Kaldi model not recognizing words

I began using Kaldi to train a model for use with VOSK in python. The issue i am experiencing is with recognizing certain words such as "manor". I have tried adding multiple variation in the lexicon file such as M AE N ER M AE N AO M AE N AA M AE…
Clinton
  • 347
  • 1
  • 2
  • 14
0
votes
0 answers

Understanding Lexicon FST in yesno example of Kaldi

I am running yesno example in Kaldi. I could get 0 WER at the output, which means things are going right. However, when I tried to view the L.FST, I see some ambiguity. Consider the above L.FST , how to choose the next state from the current state…
Anantha Krishnan
  • 13
  • 3
0
votes
0 answers

How does forced alignment happen in Kaldi?

I am going through the popular 'yesno' tutorial to get comfortable with Kaldi toolkit. For acoustic model training we will need the start and end times of each utterance, the speaker ID of each utterance, and a list of all words and phonemes present…
Anantha Krishnan
  • 13
  • 3
1 2 3
4
5 6 7 8