Questions tagged [speech-recognition]
Speech recognition is the process of converting the spoken word to text, usually without regard to a particular speaker (which is more commonly referred to as "voice recognition").
192
questions
0
votes
0
answers
12
views
Understanding Feature Extraction in Automatic Speaker Verification (ASV)
I'm just starting out in the domain of automatic speaker verification, speaker recognition research. Based on the literature I've reviewed, I've summarized my understanding of feature extraction in ...
0
votes
0
answers
12
views
Looking for UBM-GMM trained on the TIMIT database
Hello I was wondering if there was any publicly available pretrained UBM-GMM on the TIMIT acoustic-phonetic continuous speech corpus.
- 25
0
votes
1
answer
43
views
Simple speech recognition with hmm
I'm new to the field of Machine Learning and currently watching some lectures on speech recognition. I'm attempting to write a simple class implementation for a speech recognition model using Hidden ...
- 1
0
votes
0
answers
11
views
Close embedding similarity issue in Korean speaker verification using X-vector
I'm working on a speaker verification system using X-vector on Korean speakers' data. On unseen data, the system achieves fairly good EER (from 10% to 20%), but I'm encountering a challenge with close ...
2
votes
2
answers
433
views
What is the explanation that filter EQ changes "Ah" to "O"?
I recorded myself saying "Ah" in the tone of the note C3 which is about 130Hz, this is what it looks like:
Then I ...
- 135
0
votes
1
answer
79
views
How can sound waves be modeled in a manner that distinguishes individual voices but also recognizes words?
More specifically, I'm curious how we can represent sound waves in a way that would both distinguish between individual voices and also recognize, e.g. that recordings of different people saying the ...
1
vote
0
answers
26
views
What is gained by transforming a convolution to an addition with the cepstrum?
In automatic speech recognition the spectrum $f$ is interpreted as the convolution of elicitation $e$ and impulse response $h$.
By applying the cepstrum $cep(f) = FT^{-1}(log(FT(f)))$ this convolution ...
- 111
0
votes
1
answer
135
views
Which DCT implementation is the correct one
I'm trying to compute the Discrete Cosine Transform via FFT in C, using a response to this question, but the recommended solution gives me wrong results.
Function DCT in matlab:
...
- 3
0
votes
0
answers
55
views
How to decided the score threshold in speaker recognition?
I am new to speaker recognition and now starting from the GMM-UBM algorithm.
Say I have a pre-trained UBM and speech from target speakers ...
- 21
0
votes
0
answers
28
views
How can I speech enhancement with DNN?
I want to do speech enhancement with DNN on Matlab. I downloaded the TIMIT dataset from the internet as a .wav file. I also downloaded the noises from the Noisex-92 database as .m file. Now I need to ...
- 59
-1
votes
1
answer
94
views
How do I detect by ear if a quarter second audio clip is that of someone speaking or not?
I have a dataset of quarter second 16 bit mono PCM audio clips, each clip labelled as speech or nonspeech. I am trying to estimate the quality of the labelling by randomly sampling a few of them and ...
- 99
1
vote
2
answers
114
views
What are the fundamental differences between speech and music in frequency domain?
What are the fundamental differences between speech and music in the frequency domain?
I can think mainly of features in the time domain that can differentiate speech from music signals, e.g. short ...
- 111
2
votes
0
answers
37
views
Finding "Max Change" in a Audio Signal
I'm working on studying an endangered language and have the following problem: while I already have labeled exactly what the speakers I worked with have said at given timesteps on the word level and I ...
- 121
0
votes
0
answers
41
views
Automatically identifying speech disfluencies from audio recordings
I want to automatically identify speech disfluencies (e.g. um(s) and uh(s) ) from my speech recordings. I am a bit surprised I couldn't find any disfluency detection models using speech only. I know ...
- 103
2
votes
1
answer
697
views
How to compare 2 MFCC (compare them if they where created from same speaker)
There are multiple speakers.
Each speaker generates multiple MFCC.
If I'm getting two different MFCC, can we know if those MFCC came from 2 different speakers or same speaker ?
How can we compare ...
- 121
0
votes
3
answers
402
views
Formant analysis LPC (Matlab)
I wanted to do formant analysis using MATLAB and did everything according to the following tutorial:
https://de.mathworks.com/help/signal/ug/formant-estimation-with-lpc-coefficients.html
I have speech ...
- 425
0
votes
1
answer
47
views
Does speech volume affect frequencies?
I have created a little classifier that listens for certain keywords. Sometimes it will not react to a keyword, but if I shout the word, then the classifier will be able to pick it up.
The classifier ...
- 101
3
votes
0
answers
66
views
Frame lookup using audio
I'm an animator trying to get a program that will use machine learning to automate the lip syncing process. The program I need made will have two files given to it: a seed, and an audio file.
The seed ...
- 31
1
vote
0
answers
241
views
Understanding MFCC
I am not from electrical or electronic background so my knowledge will be lacking.
MFCC is represented by 39 values for each window frame. 12 values are the mel filter-bank and we get 13th value by ...
- 111
0
votes
1
answer
620
views
Speech recognition algorithm in GNU Octave to convert speech to text (and vice versa)
Recently, I am building an application in Octave and I saw some algorithms about speech recognition spread around the net, but most of them were implemented in Python, MATLAB, C++ and no one in Octave....
1
vote
1
answer
2k
views
Removing background noise algorithm
What is the algorithm for removing background noise from an audio clip of human speech? Say I have a 10 second audio clip of somebody talking, and there is background noise of them tapping on their ...
- 153
0
votes
0
answers
33
views
Audio in Image,Graph or WaveForm Representation
Our task is to feed the audio data into the deep learning tensor flow model in the form of image representation(or graphical,waveform). Question is what is the best way of representing audio in image ...
0
votes
0
answers
1k
views
Understanding liftering as the final step in MFCCs features extraction
In the book here, they apply liftering, as a final step of MFCCs features extraction, to isolate the system component by multiplying the whole cepstrum by a rectangular window centred on lower ...
- 31
1
vote
2
answers
2k
views
MFCCs and mean normalization
I'm reading a blog about extracting MFCCs features for Machine Learning applications, but I didn't understand the following points about the mean normalization:
To balance the spectrum and improve ...
- 31
1
vote
2
answers
554
views
filterbank: understand the different responses at the center frequency of each filter
I'm computing filterbank by applying 26 triangular filters on a Mel-scale to the power spectrum of an audio frame to extract frequency bands, and I found that some references use filterbank with equal ...
- 31
1
vote
0
answers
360
views
Mixing signal with noise in frequency space (STFT)
I am working on a preprocessing function which is supposed to mix two audio signals clean and noise in the context of neural ...
- 121
0
votes
1
answer
292
views
python3: speech recognition - calculating features of a WAV file
I am supposed to do this as a school project, but I am kind of lost when it comes to signals and would appreciate your help. Also, English is not my first language, and I will be translating the ...
- 101
-1
votes
1
answer
74
views
audio classification based only on first few seconds
I record audio notes on my recorder, and each belongs to a certain category ("work", "parenting", "miscellaneous", etc.). At the beginning of each recording, I say the name of the category, then stay ...
1
vote
1
answer
48
views
Problem getting DTW to work for speech recognition
I used my ipad to record the words "This. Is. A. Test. This. Is. A. Test.", then downloaded it to my computer as a .MOV file and used ffmpeg to extract audio as WAV. I then used the tuneR package to ...
- 13
1
vote
1
answer
453
views
Preprocess sound for voice recognition in Pocket Sphinx on Raspberry Pi 3
I want to improve my voice recognition system on a Raspberry Pi 3 running Pocket Spinx.
user44829
4
votes
1
answer
3k
views
Why is the Hamming and Hanning window the most widely used for speech spectograms?
When taking the Short-Time Fourier Transform of the speech signal, windowing is applied to taper away the signal frame at both ends and mitigate introduced artifact at expense of the maximum ...
- 107
1
vote
1
answer
155
views
Audio from multiple microphones mixed to mono and ASR
I am trying to do speech recognition on an audio file which has 1 channel (mono). My problem is that the channel is comprised of the signal of 3 microphones which have captured the audio at different ...
- 11
1
vote
1
answer
99
views
Are delta and double delta features needed when classifying with LSTM
I understand that the combination of MFCCs, deltas and double deltas is a good feature to be used with HMMs for keyword detection problems. HMMs are limited by Markov Property and this limitation is ...
- 69
7
votes
1
answer
17k
views
What are i-vectors and x-vectors in the context of Speech Recognition?
I have read that i-vectors and x-vectors are widely used in speaker recognition tasks but I don't get the difference between them and how exactly they work. Can someone explain it starting from the ...
- 171
1
vote
1
answer
300
views
Calculate the Standard Deviation of Fundamental Frequency (MFCC)
I'm implementing a gunshot detector following the article "Algorithm for Gunshot Detection Using
Mel-Frequency Cepstrum Coefficients
(MFCC)" (paywall).
In the article, the authors uses 22 features ...
- 121
1
vote
1
answer
388
views
Fast Vocal Tract Length Normalization(VTLN) implementation?
My team is building a speech recognition model. As far as I know, Vocal Tract Length Normalization (VTLN) is an effective warping method that may help improve the model performance by diminishing ...
- 183
2
votes
1
answer
259
views
Is there any way that we can perform speech recognition without using Fourier transforms?
I am trying to research about speech recognition and why everyone uses Fourier transforms in going about the topic. I know that we get information related to the frequency of each sound uttered which ...
- 21
1
vote
1
answer
283
views
Split audio file into audio phrases
I have couple of audio recordings of length 5 -7 min. I also have corresponding text to each audio file.
I am not subject matter expert on speech to text but I am vaguely aware that much smaller ...
2
votes
4
answers
182
views
Cleaning telephone audio
I have telephone audio at 16kHz and I am trying to use it with a speech transcription engine that converts spoken letters to text. However, the engine has some difficulty transcribing certain letters ...
- 153
1
vote
1
answer
49
views
Services for phoneme recognition? [closed]
I wonder if anyone can point me to services or dev libraries that focus on or suit phoneme recognition? Target audience is children at learning to read stage.
We have trialed IBM Watson (not good) ...
- 113
-1
votes
2
answers
316
views
why the MFCC is gender indenpend and used for isolated word recognition
I think female and male have total different MFCC feature for same word such as "one", but why the MFCC could be used for isolated word recognition which use the same HMM model for the same word ...
- 1
6
votes
1
answer
575
views
What Is the Point of Doing the Zero Padding? [duplicate]
What are the advantages and disadvantages of doing Zero-padding, in particular the case of speech signals?
user38784
3
votes
2
answers
3k
views
MFCC window size at different sampling rates
The general recommendation for window size when calculating MFCC seems to be 20-40 msec. This is most often recommended in a context of 16000 samples per second, so leading to a window containing 320-...
- 43
1
vote
0
answers
22
views
Finding fundamental particles of sound In ASR systems? [closed]
Q1. Can we divide phonemes which are specific to a language into some more fundamental entities same across all languages ?
Q2. Will this help us in achieving language independent acoustic modelling ...
- 111
-1
votes
1
answer
838
views
Slow implementation DTW for word recognition
I wrote little program for isolated word recognition using DTW algorithm. In folder with main program i have another folder "Data20dict", with 20 more folders in it, and each one is called by voice ...
1
vote
3
answers
2k
views
How to edit audios so that they have the same length
I have a dataset of audio files, which differ on their lengths by a couple of milliseconds. Some are little shorter than 1s and some are little longer than 1s. They all have the same sampling rate, ...
- 151
2
votes
1
answer
625
views
MFCC Classification
I'm working on gender estimation from speech signal and I completed MFCC feature extraction. So now I'm trying to estimate gender from these features. But I have frames for an audio file and I ...
0
votes
1
answer
111
views
Is there a known correlation between human voice (360Hz to 5kHz) and the frequencies above/below that?
Hello SignalProcessing!
Given the important frequencies of a human voice (360Hz to 5kHz) to communicate and the frequencies above and below that make the voice sound way better.
Imagine we are ...
- 103
0
votes
1
answer
827
views
Does speaker recognition system need the same sample rate audio?
I'm a new man in speaker recognition project. I've train a model with some .wav files, its sample rate is 16000.
I want to test this model with my record, but my record's sample rate is 8000
Doed it ...
- 11
1
vote
0
answers
48
views
Is it possible to detect that sound source is playback of a recording?
I have been trying to find an article where it is described how real-time (or close to real-time) signal processing from a microphone is able to detect that an audio source is playback of a recording ...
- 11