Podcast #128: We chat with Kent C Dodds about why he loves React and discuss what life was like in the dark days before Git. Listen now.

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").

Filter by
Sorted by
Tagged with
0
votes
0answers
427 views

The essential pre-processing steps in speech signal analysis

My question is that for simulating a new scheme for speech emotion recognition (feature extraction and classification), what are the necessary pre-processing steps (I mean any kind of normalization ...
10
votes
1answer
1k views

How does noise reduction for speech recognition differ from noise reduction that is supposed to make speech more “intelligible” for humans?

this is a question that has interested me for some time now, mainly because I'm working on noise reduction for an existing speech recognition system myself. Most papers on noise reduction techniques ...
2
votes
2answers
2k views

Difference Between MFCC of speech and speaker recognition

I am doing my project on speaker recognition. One of my friends is doing his project on speech recognition. Both of us need to calculate the MFCC for feature extraction. Is the MFCC going to be the ...
0
votes
1answer
47 views

Deep learning model for phone recognition - issues with dimension the model

I seem to have some problems understandind how the model described in this paper has been designed This is what is written about the model dimension.. ...In these experiments we used one ...
0
votes
1answer
174 views

Signal Processing and Emotion Recognition

I have to write a paper on emotion recognition. More specifically on how different parameters affect the algorithms effectiveness. I have already read a lot about this and done research using ...
1
vote
0answers
125 views

difference between logged power spectrum and power spectrum?

What is the difference between a logged power spectrum and power spectrum... Well the log part. So can a normal power spectrum be converted to a logged power spectrum just by taking the log of the ...
-1
votes
1answer
795 views

Applying dtw on mfcc

I have calculated 26 MFCCs for two sample speech data. My mfcc matrices thus contain 26 columns and 120 rows each, where 120 is the number of frames. Now I want to apply DTW on them and I am doing ...
0
votes
1answer
255 views

Speech Recognition [closed]

I am new learner in the field of speech analysis. I am wondering there are so many resources which explaiins principles of speech recognition. Most of them are advanced topics. I am curious to know ...
1
vote
1answer
1k views

The minimal signal to noise ratio (SNR) for people to understand a speech in the noisy background

This question seems easy to find an answer but I got lost in the end. I am trying to find the threshold for people to understand speech in a noisy environment. For example, assume the background noise ...
0
votes
0answers
286 views

Proper way of representing Static, delta, delta delta in a plot

I am currently working on recreating the result of this paper. The paper is about applying cnn in speech recognition, in which cnn is used to for feature extraction, for which a proper way of ...
1
vote
3answers
487 views

How should this fft output be intepreted?

I am currently reading some code, so I can understand how this FFT output is actually been stored. I have a function which computes FFT of audio file, and stores is in the format. ...
3
votes
2answers
6k views

Why is each window/frame overlapping?

I am currently reading up on some speech recognition theory. As it speech signals usually are non stationary, but if a speech is seen in a very small time frame can it be deemed stationary, as would ...
1
vote
2answers
2k views

Applying a window function to a speech signal

I'm currently developing a speaker recognition system. I have two main problems: What is the most suitable windowing function to apply to a speech signal prior to the STFT? Is it necessary to apply ...
1
vote
1answer
50 views

Effect of redundant training data in HMM-based speech recognizer/synthesizer?

How are redundant training data handled during the training stage? For example, assume we have one observation for phone $\theta$ in the training set. Then the training (for a monophone) is done ...
-1
votes
1answer
3k views

Compare two audio tracks

I need to compare two audio tracks and compute the difference. The difference is how close they are in terms of pronunciation, rhythm etc. ignoring speaker voice characteristics. The first track is ...
0
votes
1answer
135 views

Word Error Rate weights

Usually ASR systems are evaluated using WER (word error rate), which summarizes 3 types of changes when calculating the edit distance: insertions, deletions and substitutions. According to the ...
1
vote
1answer
731 views

Hidden Markov Models - Distinct Observation Symbols

I really, really hope someone can help me with regards to this question. I'm trying to implement a Hidden Markov Model (based off this paper: Here I understand the processes, but, I do not ...
0
votes
6answers
420 views

Call recognition using Digital Signal Processing

We are looking for writing applications which would recognize Bird calls and Frog calls using Sound processing. EDIT: I want to identify the species of bird / frog and do not want to differentiate ...
0
votes
1answer
1k views

Butterworth filter for signal processing

I have a school project to be able to move a wheelchair according to user instruction. I am currently starting my project by using MATLAB and I have acquire several data for the training purpose. I am ...
1
vote
0answers
378 views

Gaussian Mixture Model-UBM based for image recognition

Scenario: Open set recognition: Unknown individuals may appear on scene (CCTV). Gallery = 10 individuals with a mug-shot image per individual. Approach: Gaussian Mixture Model-UBM based Use video ...
0
votes
1answer
805 views

SNR estimation in segmented speech signals

I was called to estimate the signal-to-noise ratio in a collection of recordings that were manually annotated, meaning that the speech and noise segments are known. The noise is uncorrelated with ...
0
votes
1answer
55 views

Amount of delay in audio signals which are echos of the original audio signal

Could you please inform me, in simulations and also in practical cases how much is delay in audio signals which are echos of the original audio signal (I mean the reference assumption in the ...
0
votes
1answer
63 views

Fine-grained evaluation of speech recognition results

I know that usually ASR systems are evaluated using WER (word error rate), and I was wondering if it makes sense to use a more fine grained approach. E.g. transforming both the ASR hypothesis and the ...
0
votes
1answer
198 views

Good methods for hardware based 1-2 word speaker independent speech recognition?

I want to detect, in real-time, a 1-2 word spoken phrase within continuous speech, speaker independently, in hardware. The smaller the number of gates the better. What is the best way to do this? Are ...
0
votes
2answers
122 views

Training and testing set for speech recognition

I am the moment looking for a dataset similar to the caltech 101, but in this case for different phrases, words and so on... In general just words. Does someone know if such dataset exist, or I have ...
1
vote
2answers
629 views

Why discrete cosine transform may not maintain locality

In paper Convolutional neural network for speech recognition, they say I didn't understand the highlighted sentence.
17
votes
3answers
18k views

human speech noise filter

Does anyone know of a filter to attenuate non-speech? I am writing speech recognition software and would like to filter out everything but human speech. This would include background noise, noise ...
1
vote
1answer
1k views

Voice Recognition - MFCC

I have been researching about Speech Recognition and I have decided to take the MFCC approach to solving this problem of detecting whether someone is saying either "Yes" or "No". So as mentioned ...
1
vote
1answer
4k views

Speech recognition using MFCC and DTW(Dynamic Time Warping)?

I know basics about DSP, and now trying to complete a project on Speech recognition. So I read as many resources as I found, and got some ideas. They are like: take a sample sound and break it into ...
5
votes
0answers
592 views

Zero-padding of MFCC coefficients

I am trying to implement speech recognition using backpropagation algorithm, and I have been following this paper. I have followed it all the way, except that it tells me to zero-pad the coefficients ...
3
votes
1answer
89 views

How to do continuous signal processing (i.e without windowing)?

I'm working in speech recognition research, and I wonder if there is a way to analyse sound just like how ears do (i.e. without windowing), so for example to take some feature continuously with an ...
2
votes
1answer
1k 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 ...
1
vote
0answers
1k views

What does the output of Gaussian Mixture Model (GMM) represents in a HMM-GMM based speech recognition application?

Till now I know that- first the speech is converted frames and feature vectors are calculated for each frame using MFCC. And while training the Acoustic model- HMM model is generate for each phoneme ...
3
votes
0answers
10k views

MFCC calculation

I've got a project and need to calculate MFCCs. I tried to read some tutorials and then make a MATLAB function but I seem to have wrong answers. I'd like to feed MFCCs to one of the classification ...
-1
votes
1answer
514 views

Help using vector quantization

I have a sample signal, and I computed MFCC using this code.Now I have an array of 1225x12 size, where there are 12 coefficients for 1225 frames. Now I want to test another signal against this sample, ...
1
vote
1answer
398 views

How to average MFCCs from different speakers saying the same word?

I am trying to create a simple recognition system. i have recordings of several speakers saying the same word, let's say "west". I compute the MFCC feature vectors of word "west" from each speaker. If ...
0
votes
1answer
45 views

Discrimiation between human speech and computer generated one

I'm currently working on voice activity detection (VAD) theme and I just started to wonder - if computer generated speech (as when using voice generators) can be discriminated from human speech with ...
0
votes
1answer
165 views

HMM-based speech recognition/synthesis: state representation of monophones and triphones

In literature, a monophone is represented with 3 states. When doing context dependent clustering, 3 states are used to represent a triphone. Why is the triphone represented with 3 states and not 5? ...
1
vote
1answer
76 views

Quick question about difference between two implementations of MFCC

I'm trying to learn more about voice recognition, and I was looking this library here and noticed there were two implementations of MFCC (one called mfcc and another called mfcc2). I ran both of these ...
1
vote
1answer
68 views

Why are the observation features of an HMM-based recognition/synthesis system modeled by a Gaussian distribution?

Why are the observation features (namely MFCCs) of an HMM-based recognition/synthesis system modeled by a Gaussian distribution? Even the state duration is modeled by a Gaussian in this paper: K. ...
1
vote
1answer
120 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 ...
3
votes
3answers
3k views

Using MFCC to an ANN Speech Recognition System

I'm developing an Artificial Neural Network based Speech Recognition System using MFCCs. Suppose I have 260 input nodes in the ANN, and this number of nodes corresponds to the number of MFCCs that I ...
1
vote
2answers
3k views

MFCC coefficients

I have read this, this, this, this and this as a reference for computing the MFCC for a given wave file. Although, I am sure the values look wrong. In short I followed the procedure in link 5. <...
1
vote
0answers
148 views

Word recognition with MSP430

In my DSP class at my university I have to create a simple word recognition system using the MSP430. Basically the board just needs to turn on and off an led at the commands "On" and "Off". My ...
0
votes
1answer
758 views

Averaging Different Length Speech Signal

I have around 10 wav audio files all containing same word spoken i.e. 'Hello' but all having different length. So lets say 1st file when loaded consist of 20000 samples, 2nd of 15000, 3rd of 18000 ...
1
vote
1answer
131 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 (DCT)...
0
votes
1answer
43 views

Matching two video conversations

I have two video where two person having conversation. They begin recording different times. I want to match these two videos' frame numbers, i.e. By matching audio. How can I do that?
0
votes
0answers
24 views

Role of HMM in speech recognition [duplicate]

What exactly hidden markov model does in speech recognition process? I read it is the representation of phonemes as states? What exactly is a state? Any detail article on HMM role in speech ...
0
votes
0answers
59 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 ...
1
vote
1answer
202 views

In speech recognition applications, how are different voice amplitudes handled? (i.e loud vs. quiet tones)

I am doing some research related to real-time voice/hotword recognition engines. In most current implementations, input is divided into frames (overlapping or not), and audio features are extracted ...