Speech processing is the study of speech signals and the processing methods of these signals.

learn more… | top users | synonyms

1
vote
1answer
23 views

Matching LPC frequency response to raw sample data frequency response

Background: The intention is feature/formant extraction from speech input. I have used an FFT on raw samples in the past and have done simple peak picking from a weighted average of frequencies over ...
0
votes
0answers
10 views

Is there an algorithm to search for a spoken words in a spoken paragraph?

I am wondering if there is a speech-based search that acts like the text based search. For example, you can implement a simple Edit-Distance algorithm to find the nearest match for the sentence ...
0
votes
1answer
37 views

How to overlap and add the frames after applying some modification in time domain

I am trying to apply Dynamic range compression (DRC) in time domain in MATLAB. But I am having problem in overlapping and adding the frames. Here is my work: ...
0
votes
1answer
40 views

Answering Machine vs. Human — Neural Network Features Selection

I've been tasked with creating an artificial neural network that can classify a telephone call as either answered by a human or an answering machine. My knowledge of audio processing is, mildly put, ...
-1
votes
1answer
49 views

how to extract pitch contour of a speech by matlab?

I am totally new in Matlab. Can anyone please explain in details how I can extract pitch contour of a speech? I would like to observe how the speaker's pitch varies during his speech to know whether ...
0
votes
0answers
21 views

How to analyze baby speech time series

I've been collecting speech data for my baby brother (who is now 6 months old) with the intention of doing computational analysis of the development of his speech patterns. I haven't much deep ...
1
vote
2answers
30 views

Speech corpora for VAD

I'm doing a student research project connected with VAD. And I want to find speech corpora with added noise. I found many references to the NIST Speaker Recognition Corpora. But unfortunately, all ...
0
votes
0answers
23 views

How can I prove this equality

considering the following equation $$h(n)=\sum_{k=1}^{p}a_{k}h[n-k]+G\delta(n)$$ where $\delta(n)$ is impulse function. if autocorrelation function as follows $$R(m)=\sum_{n=0}^{\infty}h(n)h(n+m)$$ ...
0
votes
1answer
73 views

Calculating Delta MFCC, correct formula?

I have seen different formulations of how to calculate delta mfccs. In general, I want to be consistent in such a way that if have other features to look at other than mfccs, the way I would ...
1
vote
1answer
50 views

Using 8 bit samples for speech comparison

I am making a speech comparison app in javascript. I found this dsp.SE post: Speech comparison algorithm for rating on similarities, where I read it is best to use mfcc and dtw algorithms. I ...
0
votes
0answers
28 views

Regarding maximizing signal to noise ratio

If I have 3 recordings, each of speech (recorded in a relatively silent room), speech+background noise and background noise then is there a way to utilise the data from all the three to extract clear ...
0
votes
1answer
45 views

Computing of speech signals modulation entropy

I got a question regarding to modulation entropy of audio signal. There is some literature I found about this topic, http://www.irit.fr/recherches/SAMOVA/FeaturesExtraction.html#me. I've read sample ...
1
vote
1answer
29 views

What are good estimates for phonemes length?

I am working in a phoneme recognition project, the language that I am using is "English". I have a tool that converts each written phrase in phonemes. Also I have an estimation of the time length of ...
1
vote
1answer
20 views

Recursively obtaining all-pole coefficients from complex cepstral coefficients?

This is a problem from the book Discrete-Time Speech Signal Processing by Thomas Quatieri, Chapter 6 Problem 13: Suppose $h[n]$ is all-pole (minimum-phase) of order $p$. Show that the all-pole ...
0
votes
0answers
20 views

LPC analysis without implicit windowing

In MATLAB, the documentation for the LPC function states: lpc uses the autocorrelation method of autoregressive (AR) modeling to find the filter coefficients. ...
0
votes
0answers
27 views

Recovering spectrum from vowel-sounds

I have this working: https://gist.github.com/p-i-/6e5ab73820b6368a331a The output looks like this: The basic algorithm is as follows: ...
-1
votes
1answer
50 views

How do I efficiently process 20+ minute audio tracks? [closed]

I have built something that reads in audio files and processes the information for features. Sometimes the audio is rather long, and obviously I cannot keep all of this information in RAM. How can I ...
-1
votes
2answers
90 views

If we FFT a signal with number of points far less than the length of the signal, the result is unreliable?

For example, there is a very long-term observation and I cut the signal at a sampling rate of 10 into many segments of 1e6-point ...
0
votes
0answers
30 views

Unique feature value for each phoneme

I'm working in a speech recognition project for the university. I'm using the TIMIT dataset and pylearn2 as machine learning library. The project need to be simple, and it doesn't have to follow the ...
0
votes
0answers
22 views

Room Impulse Response for CHiME speech database

Where can I find the .wav file or a MATLAB plot for the Bin-aural Room Impulse Response(BRIR) that is used to create the CHiME speech database? http://spandh.dcs.shef.ac.uk/chime_challenge/data.html ...
0
votes
0answers
67 views

Speech signal, Word Boundary algorithm

I need to implement an algorithm in Matlab that, given a speech signal contaminated with background noise, can detect the boundary of each word, saving only the samples that belong to the actual ...
0
votes
1answer
35 views

Bandwidth of time-varying harmonics of speech

For speech signals, do the harmonics have a constant bandwidth above some threshold (arbitrarily, -6 dB dropoffs)? Or does this bandwidth decrease with the upper harmonics? If this is not known, how ...
0
votes
1answer
196 views

Initialize a Room Impulse Response using reverberation time(T60)

I am doing Speech dereverberation using Non-negative matrix factorization. I need to initialize an impulse response($H$) such that its reverberation time ($t_{60}$) is $300$ ms. Let the length of $H$ ...
0
votes
1answer
218 views

Phone conversation diarization with LIUM

I am trying split call-center recording by speakers. LIUM seems to fit great. But results look random to me (green is etalon, gray is what I get): So I think I am doing something wrong. Maybe ...
0
votes
0answers
46 views

Invertible multi-resolution representation of audio/speech signals

What are the invertible (preferably linear) representations of an audio/speech signal which captures the essence of signal in different resolutions and details. Basically, I am looking for ...
0
votes
0answers
26 views

how to cancel echo with adaptive filter, but without using reference

Ι am trying to cancel echo present in speech. The input is to a single microphone in an auditorium . I am trying with an adaptive filter and as per this method a far end signal provides a reference. ...
0
votes
1answer
138 views

Division by zero in Levinson–Durbin recursion?

I am doing a LPC analysis of a speech signal using the autocorrelation method. To calculate the LPCs I am using the Levinson–Durbin recursion. In my literature the error is initialized with the first ...
0
votes
0answers
45 views

How to detect impulse noises in audio recording?

How do you detect impulse noises in audio recordings of speech? By "impulse noise" I am thinking about noises like: Typing on a keyboard A door slamming Somebody bumping into a table Tapping on a ...
0
votes
0answers
41 views

How to get rid of speaker dependent information from MFCC

I'm trying to use MFCC vector features in order to compare the same words spoken by different persons. Is it enough to set a starting frequency for MFCC algorithm to 300 Hz, in order to get rid of ...
0
votes
1answer
21 views

Data representations for speech data

I'm interesting in knowing more about different kinds of data representations that are used for speech data. I know of FFT, but not any others. More precisely, I have the 3 following questions. What ...
-3
votes
2answers
59 views

Problem in reading speech waveforms

I have two waveforms, and I'm not sure which of them is for the word "cease" and which one for "shoot". Now I guess based on voiced and unvoiced waveforms(voiced should be periodic), the first one is ...
0
votes
0answers
105 views

Which algorithms one can use for matrix inversion (for beamforming application MVDR/LCMV) in Fixed Point?

I have implemented beamformer(MVDR/LCMV) for speech enhancement in matlab, now I am trying to convert it to fixed point implementation. during the weight calculation step correlation matrix inversion ...
1
vote
1answer
67 views

What is the difference between neural network and deep neural network. an example thank you [closed]

What is the difference between neural network and deep neural network in speaker recognition .Can i have an example of code sur Matlab thank you
-1
votes
2answers
167 views

Invert soundsc function in Matlab

Does anyone know what is the inverse function of soundsc in matlab. I'm playing a sound with a my PC microphone using soundsc, ...
0
votes
2answers
1k views

Simple VAD (Voice activity Detector) implementation

I am to classify few recorded phone calls as either containing speech or not by sampling lets say first 10 seconds. The files contain either silence, dialtone or ringtones, or real human voice. I ...
0
votes
0answers
72 views

MATLAB band-stop filter design for room reverberation?

I took acoustic measurements of a room using sine swept method, and I also used Pioneer sc-37 to obtain more accurate data. I used RoomEQ wizard software and measured the impulse response of the ...
0
votes
2answers
123 views

How to take acoustic measurements of a clasroom

I'm an electrical engineering major and I have a question regarding a project I'm working on. I'm supposed to design 3 band-stop filters on MATLAB for echo cancellation/suppression. My problem is ...
1
vote
1answer
113 views

Markov processes

I am trying to read a paper and I found it difficult to understand. This is a quote: Standard Mel frequency cepstrum coefficient (MFCC) computation technique utilizes discrete cosine transform ...
2
votes
1answer
280 views

Detecting phones in a word audio

I am working on speech recognition for Hindi language. My approach is to map speech to text based on phones. For this, first split the speech into the words and then map each word to text by detecting ...
0
votes
1answer
617 views

removing vocal from audio file

I want to create a program in matlab that could act like karaoke software. At this moment i have following lines of code: ...
0
votes
1answer
191 views

autocorrelation A to K conversion for LPC speech analysis?

I am building an LPC analysis tool for speech synthesis and did the following to generate my a0 through a10: ...
0
votes
1answer
117 views

Speech recognition and comparison algorithms

I am doing several research for a prototype which I will be building. My prototype will consist of single word speech recognition and comparison with a preset recorded words. The prototyped system ...
0
votes
1answer
53 views

Pesq numbers and clean speech comparison to processed speech

I am trying to evaluate my processed speech for my DSP project. My project is an implementation of an MMSE algorithm proposed by Y.Ephraim and D. Malah, "Speech Enhancement Using a Minimum Mean Square ...
0
votes
1answer
65 views

Phase Estimation in speech enhancement

I am reading a recent paper titled "Phase Estimation of Speech Enhancement - unimportant, important, or impossible?" by Grekmann et al. published in the 2012 the IEEE convention. The paper proposes an ...
0
votes
2answers
466 views

'A priori' and 'a posteriori' SNR

I am reading this paper about speech enhancement using a minimum mean square error short time spectral amplitude estimator for our speech enhancement project. Basically in the paper they mix a clean ...
0
votes
1answer
79 views

What is the distance metric in dynamic time warping?

I am reading the lecture slides from this site http://luthuli.cs.uiuc.edu/~daf/courses/CS-498-DAF-P/Lecture%2018%20-%20Time%20series,%20DTW.pdf In slide 24, the lecture suggest using metric of the ...
1
vote
1answer
84 views

Filtering noise and identifying phones boundary in speech recongition

I am planning to do a self project on speech recognition for a vocabulary detection system using arduino. I know CMUsphinx or bitvoicer is probably the way to go. But I would like to code the project ...
1
vote
0answers
93 views

Features for speaker recognition

I'm trying to create my own program for speaker identification (text-independent) and have used MFCC features for that. But result of recognition is very poor. My supervisor told me that using MFCC ...
0
votes
1answer
86 views

Variance of white noise and the STFT

I hope someone can help me understand the meaning of variance in this case. I am reading an old research paper by Ephraim and Malah (for my DSP project) and it says: Knowing that $D_k$ is the FFT ...
0
votes
0answers
19 views

Why the formula below are critically-damped second-order linear systems?

This is part formula of command-response model (Fujisaki Model): ...