Questions tagged [speech-processing]
Speech processing is the study of speech signals and the processing methods of these signals.
272
questions
1
vote
0
answers
24
views
In "Mel spectrogram" or "Mel filterbanks", what does Mel mean and why is it often capitalized? [closed]
In "Mel spectrogram" or "Mel filterbanks", what does Mel mean and why is it capitalized ? It doesn't seem to be the name of a person.
- 111
0
votes
0
answers
18
views
Formant bandwidths
I have some intuition about bandwidths from these videos (1 and 2) explaining how the frequency response corresponds to the Z-surface.
The only thing I could find on the internet about calculating the ...
- 378
0
votes
0
answers
52
views
How do I eliminate background noise？
After I use deep learning algorithm to enhance the speech, the speech will still have a weak background noise.The background noise of this audio has little effect on the calculation of SNR, but it ...
- 13
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
2
votes
1
answer
150
views
Is it possible to calculate DRR (Direct Reverberant Ratio) from an Room Impulse Response? If not, how is this parameter calculated?
DRR (Direct-to-Reverberant Ratio) and Reverberation time (T60) are said to be two of the most important characteristics of sound in Reverberation. DRR is said to be ratio of the energies of the direct ...
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 ...
1
vote
1
answer
218
views
How to calculate the reverberation time RT60 given dimensions of a room?
I'm trying to estimate RT60 based on reverberant sound. In order to generate reverberant sound, I am required to give dimensions of a room so that RIR is generated and is convolved with clean sound.
...
2
votes
2
answers
434
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 ...
9
votes
5
answers
808
views
Identify abrupt changes in an audio waveform
I have an audio file which was created by substituting multiple speech segments into an original utterance.
I want to find the timestamps where such substitutions happened, so I guess that one thing I ...
- 143
2
votes
0
answers
41
views
Global gain and frame gain in audio and speech processing
I'm wondering if there is a standard definition for global gain and frame gain in audio and speech processing. I found these terms together with an imprecise definition in a text about bandwidth ...
- 21
0
votes
0
answers
157
views
Good models to separate speech and noise?
I have an audio clip containing speech and noise. I want to separate the noise signal from the speech signal.
I've looked at some deep-learning based models, but they only remove the noise, without ...
- 1
1
vote
1
answer
134
views
Implementing Statistical Pitchmark Correction Method formula in programming code
I am trying to follow along a paper: The IVO Software Blizzard 2007 Entry: Improving Ivona Speech Synthesis System
This paper explains how automatically estimated pitchmarks (certain time periods in ...
- 61
2
votes
1
answer
71
views
What are some speech features that vary with what the speaker says?
I have been working on a text-dependent speaker verification project. I have used mel-frequency cepstrum coefficients(MFCC) for the project. As far as I know, MFCC coefficients depend on the vocal ...
- 41
2
votes
1
answer
94
views
MFCC: Does the DCT discard the information on pitch?
Given that the pitch harmonics of speech, are higher frequency features than the spectral envelope (of the pitch harmonics), I had an idea that computing the DCT of a spectrogram and discarding the ...
- 378
0
votes
0
answers
56
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
39
views
How to generate PSHC carrier used in vocoders
Vocoders are often used to acoustically simulate the information transmitted
by a cochlear implant. The different types of vocoders used in cochlear implants include noise-vocoding, sine-vocoding and ...
- 293
3
votes
3
answers
226
views
Using spectogram to speed up a signal - Time Scaling/Phase Vocoder
Background
About half a year ago, while learning about spectograms as part of an Image Processing course I took, I was told you can speed up audio using spectograms as follows:
Calculate the ...
- 89
2
votes
0
answers
50
views
Looking for audio/speech filtering expert for mobile hearing app
I am an Ear-Nose-Throat doctor (hearing doctor), looking for some help from someone who has built a mobile app with Frequency Filtering and Amplification. I am working on a social impact program for a ...
- 21
0
votes
0
answers
55
views
How does phase spectrum compensation works?
I'm trying to find some information that explains how phase spectrum compensation of non-stationary signals methods works, but I can't find an exact description of the procedure. I can't understand ...
- 113
1
vote
1
answer
53
views
Similar voice features for imitated voice
What kind of audio signal features/properties are appropriate for signal similarity measurement invariant to imitation?
Basically I would like to do the following:
Having a template (e.g. a spoken ...
- 156
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
vote
1
answer
127
views
Should i use window with hop_size in Wavelet Transform or Discrete Wavelet Transform?
I have a signal (audio - voice) with 1 second of duration with sample rate of 50000 Hz. It is big signal and I wish extract some features and apply pattern recognition or classification.
My question ...
4
votes
1
answer
147
views
Which Programming Language Should Be Used for Deep Learning (Deep Neural Network [DNN])?
I will do voice activity detection and speech enhancement based deep neural network. However, I don't know whether to do this via matlab or pyhton. In which programming language can I find more ready-...
- 59
0
votes
0
answers
98
views
Realtime Independent Vector Analysis
I have been working on an implementation of Real-time (Online) IVA (independent vector analysis). The paper I am referring to is: Real-Time Independent Vector Analysis for Convolutive Blind Source ...
0
votes
2
answers
50
views
Eliminate different microphones textures from their recordings
In my setting, I have different microphones recording a same speech signal. For each microphone recording, I can feel a slight difference in the playing sound. I am calling this property of a ...
0
votes
0
answers
120
views
Calculation of ITD (Interaural time delay) using linear prediction - python
How is it possible to calculate the interaural time delay between two signals recorded underwater (ship sound signals)? Will linear prediction weight method be used for this?
- 101
0
votes
0
answers
352
views
How can we find Room Impulse Response in real-time using Sine Sweep Method?
I want to calculate the room impulse response in real-time using sine sweep method. For that, I generated a sine sweep $x$ & its amplitude modulated inverse signal $f$. Then I played that $x$ ...
2
votes
2
answers
1k
views
How to use deconvolution technique to find out impulse response?
I have been working to find out room for impulse response. I am using Logarithmic sweep sine wave as input say $x(n)$ and my recorded signal is $y(n)$. I know the room impulse response is ...
- 121
0
votes
0
answers
59
views
Voice glitch while selecting signal to play from a series incoming recorded signals
In my setting, I have multiple microphones recording the same speech signal in real-time.
The speaker is moving while speaking.
I am selecting one of the recorded signal to play based on their RMS ...
1
vote
1
answer
86
views
What is the "chirped response FIR filter"?
In Pitch synchronous split-band LPC (PS-SBLPC) vocoder the authors describe an algorithm to identify pitch cycle boundaries. In "Pitch cycle detection" section, this sentence describes ...
- 111
3
votes
2
answers
1k
views
What is a "pitch period"?
The term pitch period appears in the book Speech and Language Processing by Daniel Jurafsy:
As we just said, a pitch-synchronous algorithm is one in which we do
something at each pitch period or ...
- 133
0
votes
0
answers
33
views
with PCM-16 no speech sound
I am trying to create a synthethic speech dataset. A quick overview of the my process is:
read wav
apply stft
do some stuff (ex. add noise, etc.)
apply istft
write wav
Now, the .wav file that I am ...
- 101
0
votes
0
answers
92
views
Is there a technical term for smoothing or flattening the floor of an amplitude envelope?
I am working with the speech envelope, and I have been trying to make it act a little more like a bilevel signal by exaggerating the peaks and flattening out the floor.
I detrended and smoothed my ...
- 33
0
votes
1
answer
40
views
How is voice sound on TV or phone distorted through a face mask?
After a year of listening to people talk through face masks, it appeared to me that the sound is not merely muffled, but it has a very specific and recognizable tinge and texture to it.
It reminds me ...
- 171
1
vote
2
answers
116
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
-1
votes
1
answer
79
views
Amplification of a speech signal in the recorded audio
I have recorded an audio.
I dont know how it happened that only one sided speech is recorded and the other speech is recorded with a very low sound. Is there any solution to amplify the other side ...
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
1
vote
0
answers
58
views
Splitting Arabic speech by letter
I have the audio stream below, which is a recording of Arabic. I am trying to split the stream into individual letters. I have manually marked the ideal locations with black lines in the image below. ...
- 141
0
votes
1
answer
55
views
Sound recording anonymization
I want to study stress based on sound recordings. However, there are many concerns about keeping the identity of the recorded persons anonymous.
I want to keep intensity and spectral contents intact ...
- 701
1
vote
0
answers
87
views
Logarithmic Amplitude Spectral Subtraction
I'm diving into audio processing and I'm trying to wrap my head around spectral subtraction. I learned there are different approaches do it based on power, magnitude, oversubtraction. My task is to ...
- 9
0
votes
1
answer
335
views
How to select the order of LPC to model formants?
I am having some difficulties understanding LPC and speech processing in general. The professor asked us to provide an heuristic way to select the order of LPC? For example if I wanted to model 3 ...
- 103
0
votes
1
answer
261
views
Male and female voice spectrum
I have a set of data which consists of male and female voices. They are pronunciation of a same sentence. What's the appropriate method for getting an average spectrum for the male and female voices ...
- 726
-1
votes
1
answer
102
views
How can you perform echo cancellation on features of audio signals?
I am working on a project that takes some features of audio signals and classify them with a neural network. However, the audio signals are added with their own echo with the environment. What would ...
- 11
2
votes
1
answer
711
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
1
vote
2
answers
59
views
Why are males' pitch lower than females?
Hi :) I'm not sure this is the right place to ask this question, but I'll try anyway:
Here are two well-known facts, and I don't understand how they work together:
Males usually have deeper voices ...
- 113
0
votes
3
answers
406
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
1
vote
2
answers
666
views
Non-Uniform Quantization
I was reading a research paper on companding schemes for non uniform quantisation. In paper one of the motivations for non-uniform quantisation is that distortion at larger amplitude values is less ...
- 11
0
votes
1
answer
215
views
Determining statistically the bandwidth of a signal from a spectrogram
My question is how to determine the parameters of a signal from a spectrogram statistically. The most important parameters that I am looking for are the lower and higher frequencies of the signal. I ...
- 173