Audio - Science topic

Hello colleagues

What are the differences and what is the indication of each audio encryption test such as SNR, Spectral Segment SNR, Peak Signal to Noise Ratio, Linear Predictive Code Distance, Log Spectral Distance Measure, Cepstral Distance, UACI and NSCR Analysis, Root Mean Square (RMS), Crest Factor, and mean square error?

Thanks

Hello colleagues

What are the differences and what is the indication of each audio encryption test such as SNR, Spectral Segment SNR, Peak Signal to Noise Ratio, Linear Predictive Code Distance, Log Spectral Distance Measure, Cepstral Distance, UACI and NSCR Analysis, Root Mean Square (RMS), Crest Factor, and mean square error?

Neural networks recognise speech, that is, they turn speech audio signals into text. This is far from my expertise, I will assume though that the input is the amplitude of the signal over time. How is the input delivered in the system in the course of time? Is it in chucks, and if yes how long are they, or does it take one data point per time?

I'm working on a project on speech recognition of ALS patients.

I am a beginner in this field. I want to learn basic audio deep learning for classifying audio. If you have articles or tutorial videos, please send me the link. Thank you very much.

I will be interviewing clergy members.

I would like to get them to make a vocal sound related to a texture. This would have them use their voice to answer the question and I would collect the audio recording to use as research in my paper.

Thank you,

Colm

Why not ? We suspect the answer might be useful for calculating reverberation time in addition to sound intensity field in audio rooms of different geometries.

1.I am researching on producing Spatial Audio on Loud Speaker.Hence i am trying to learn how it is relating to Filters.

In ERP P300 recording ( Audio stimulus), the P3 wave shows up as double hump, where to pick Peak for Amplitude and latency?

Hello everyone,

Could you recommend courses, papers, books or websites about wav audio preprocessing?

Thank you for your attention and valuable support.

Regards,

Cecilia-Irene Loeza-Mejía

Does anyone know any real free online tool, software, or application for the purpose of transcribing recorded conversation and audio files?

I'm conducting conversational analysis research based on a corpus collected from EFL learners. I'm beginning to wonder if there is any free online tool for the transcription of audio files?

I'll be grateful if anybody can help

I am doing linguistic research into the songs of a minority language and would appreciate any suggestions of books/papers covering methodologies for conducting such research. I have audio recordings of songs with transcriptions and translations and would like to start detailed analysis. Thank you.

Dear colleagues and experts

When I encrypt audio using one of the chaotic map for example logistic map and then DNA cryptography rules, how can I estimate the keyspace of all system

Thanks

We've been all round the houses with this one, and apologies if there is already a thread around this, but I can't seem to find a decent answer.

We've tried using Audacity to record interviews in this way, but it only records the interviewee, and not my questions to them. I need something that will record everything that I hear in my headphones while I'm conducting the interview - which of course is my own audio, and audio from the interviewee.

This is probably a newbie question - but any ideas?

Many thanks for any helpl/advice

Mark LIddle

Given a music audio file, I want to find out it to which genre it belongs to. To do this i want to know what the most important features to be extracted from the audio file to feed to a classification algorithm.

If anyone has worked on this type of work, please share your experiences.

Regards,

Sudheer

Hello everyone,

I am looking for links of audio datasets that can be used in classification tasks in machine learning. Preferably the datasets have been exposed in scientific journals.

Thank you for your attention and valuable support.

Regards,

Cecilia-Irene Loeza-Mejía

I use some applications, but I seek more useful options. I wonder you're the applications that you are used to and your experiences with them. Thanks for your replies in advance.

I was trying to build the model but while transforming the wav files to spectrographic images it was taking quite a long time. In 7 hours I was able to convert only 1500 wav files out of 27000. And then my system crashed. If I were to do it once more it's going to take around 4 days and I don't think that's feasible. Can someone help.

I’m looking for a camera trap that can be set out in the field to function as a camera trap but can simultaneously be programmed to take a video with audio for a set time each day. Does anyone know of a camera trap that has this capability?

Hi everyone! I’m looking for an open software toom to convert .mp3 audio files to text. We are analizing oral narratives from children and our raw data are audio recordings. while this seems pretty straightfprward, we haven’t been able to find a free software that solves this properly.

thank yo so much for you help!

I am looking for the best online teaching platform (due to Covid-19).

The features I need would be to

1: share audio, video lecture utilizing less data (due to problems of data costs for the students in developing countries)

2. bear weaker/interrupted internet signals during live lectures.

3. Offcourse free of cost.

Need comments,

Best wishes,

Zeshan.

Can we use the NPCR and UACI to test the robustness of audio encryption against differential attacks? What is the range of these two for a good encryption system?

I am working upon audio-video data to detect anomalies. I want to know that between audio and video, if audio detect anomaly and video does not then what is probability that audio detect correctly or video detect correctly?

porter stemmer algorithm is used by python for English and other languages

but i want to create stemmer algorithm for local language hoe i can

i want full resource like book, video,audios etc.

I am using a speech in noise task called the BKB sentence test (Australian version). At this stage, Audacity had enabled me to slice a large audio file into very precise trials (.wav files) so that I can include them in a PsychoPy experiment and align them with an eye tracker to get pupillometric recordings.

I now need to adjust the two channels of each trial to precise signal to noise ratios (SNRs) and combine the 2 channels into 1 channel .wav files before inclusion in my experiment. I want to have SNRs at 4 levels.

I can't seem to find a way to do this in Audacity. But it seems like something that should be relatively easy, if I knew the right place to look...

Thanks in advance for any advice

Jennifer

I have an audio file running in the format of mm:ss, but i want an audio file to run in this format mm:ss:msms(milisecond). I have used this format of converting by VLC media, but it is not running. LINK: https://www.youtube.com/watch?app=desktop&v=A9yq8qT0hqY

So is there any way I can get audio file in miliseconds also?

It will be a great favor

Hi, I am currently working on a project which requires me to implement the ICA algorithm in real time, to be specific, I am trying to separate the noise from the audio. When I perform the algorithm in offline, it works fine despite the amplitude of the separated audio is a bit soft. However, when I implement it in real-time, the separated audio becomes very soft. Any source code that I could refer to solve this kind of problem. Thanks.

Is it possible for an audio tone to be shifted by some factor due to the change in temperature in between the transmitter and a receiving microphone?

Hi

I’m looking for a solution for 2 way audio connectivity between a remote site with wireless headphones and a PC. In the remote site there is only possible to get power from a POE (Power Over Ethernet). The PC contains our own backend software and application.

Is there a solution based on Wi-Fi headphones?

What suggested communication software to use (WebRTC?)

Any other ideas?

Thanks

Doron

Hello,

I have been working on a project where I have to mix multiple audio signals of the same source coming from different slave smartphones on one master smartphone in a distributed way. Now I have aligned multiple audio packets (Packet level synchronization) in real-time (still unable to do sample-level synchronization) but when I mix them I get a comb filter effect.

My packet contains 40ms of data at a sampling rate of 48KHz. How can I eliminate this effect?

I am more into ways of making it smooth rather than subtracting delayed signals? Is there any kind of filter somewhat "AntiComb Filter" to make this happen?

Regards,

Khubaib Ahmad

Dear all,

Please find the call for a special issue on " Machine Learning Applied to Music/Audio Signal Processing" in MDPI Electronics at

Thanks and we are looking forward to your contributions!

---

Dear Colleagues,

The applications of audio and music processing range from music discovery and recommendation systems over speech enhancement, audio event detection, and music transcription, to creative applications such as sound synthesis and morphing.

The last decade has seen a paradigm shift from expert-designed algorithms to data-driven approaches. Machine learning approaches, and Deep Neural Networks specifically, have been shown to outperform traditional approaches on a large variety of tasks including audio classification, source separation, enhancement, and content analysis. With data-driven approaches, however, came a set of new challenges. Two of these challenges are training data and interpretability. As supervised machine learning approaches increase in complexity, the increasing need for more annotated training data can often not be matched with available data. The lack of understanding of how data are modeled by neural networks can lead to unexpected results and open vulnerabilities for adversarial attacks.

The main aim of this Special Issue is to seek high-quality submissions that present novel data-driven methods for audio/music signal processing and analysis and address main challenges of applying machine learning to audio signals. Within the general area of audio and music information retrieval as well as audio and music processing, the topics of interest include, but are not limited to, the following:

- unsupervised and semi-supervised systems for audio/music processing and analysis

- machine learning methods for raw audio signal analysis and transformation

- approaches to understanding and controlling the behavior of audio processing systems such as visualization, auralization, or regularization methods

- generative systems for sound synthesis and transformation

- adversarial attacks and the identification of 'deepfakes' in audio and music

- audio and music style transfer methods

- audio recording and music production parameter estimation

- data collection methods, active learning, and interactive machine learning for data-driven approaches

Dr. Peter Knees

Dr. Alexander Lerch

Given a huge dataset of audio signals say of 10s or 60s ( which contains songs, recitation, political speeches, etc. ), are there traditional ML or deep learning techniques to cluster those audio files automatically ?

If so, what platforms have you had success with?

I need suggestions for research topics that involve both speech and image, that use/need expertise in both speech/audio and image.

My background is in Speech/Audio enhancement and separation. I want some suggestions for using my background in Natural Language Processing topics.

Hello. I am conducting a psychological research study with participants in the UK, and I want to know what privacy and data protection rules there are about recording participants' microphone audio and camera video for research purposes. We have a video-conferencing simulation with a virtual human (recorded actor) and would like to record short clips of participants' audio and video during the video interaction. Is this possible, and, if so, what types of informed consent and data protection need to be provided?

Thank you so much.

We know that the pre-processing of speech recognition includes echo cancellation, de-reverberation, audio enhancement, noise suppression, and so on. Is there a comprehensive toolbox/code for that purpose that can be a start point for a beginner?

I have an audio set, and I have to determine the normal and abnormal sound. I have preprocess the audio data using MFCC. I got output as (audio Files, MFCC coefficients, MFCC vector, 1). When I passed this input to convLSTM, it shows an error that it requires five dimension input. But I am passing 4 dimension input. So how can I increase the dimension or is there any way to pass 4 dimension input to convLSTM.

Kindly guide me.

Regards

I am working on audio dataset. The dataset contains train and test audio files. The train audio file contains crowd environment where only human are murmmering and chattering. The test data contains these chattering voices of human alongwith gunshot, car passing, and accidents.

My question is which features are good for extracting information from this kind of training data who has no specific sound, just the chattering voices?

Regards

I have an audio dataset. I have process it and built an array as:

(audio Files, number of features, feature vector, 1)=(18, 64, 1688, 1)

But when I pass this to my model (file attach below), It shows me following error:

And when I again reshape it to get ndim=5 as:

It again gives me an error says that:

I do not know how to resolve this issue, and I have follow this link that https://stackoverflow.com/a/47665700/12559855 but my issue is not resolved.

Kindly guide me in this regard. It will be a great favor.

We have several video and audio files that we would like to annotate to create a scoring algorithm. We would like to know what applications (mobile or web) or annotation tools researchers are using in order to make an informed choice.

Thank you very much for all your advice,

We need your help to evaluate a deep learning model for audio restoration. Please fill in this survey (it only takes 20 minutes) or share it with your network. https://lnkd.in/gYY-32P Thanks a lot.

Hello! I am hoping to find a speech recognition tool that can automatically determine the length of each speaker's speaking turn in seconds, based on an audio or video recording of a conversation. I'd like to know the average length of each person's speaking turn in a given recorded conversation. Also, I'm looking for an accurate measure of how much overlap there was between different speakers. Ideally, the tool would automatically detect that multiple speakers were talking at the same time, and give me either a percentage or number of seconds in the conversation sample that more than one person was talking.

I am trying to build a voice cloning model. Is there some scripted text I should use for the purpose or speak anything randomly?

What should be the length of the audio and any model suggestions that are fast or accurate?

I am doing Qualitative Research

Hello, I have 26 hours of audio data. This is huge data to manually label every 2s data frame as a scream or not. Is there any idea to do at least a portion of it automatically to save time?

Hello,

I would like to apply an self-attention mechanism on a multichannel audio spectrogram, so a 3D tensor. In the original Transformer paper, self-attention is applied on vectors (embedded words) within a kind of temporal sequence. On my multichannel spectrogram, I would like to apply self-attention both on the temporal and frequency axes, so that the analyzed vectors are "through" the channel axes.

On tensorflow.keras MultiHeadAttention layer, there is a attention_axes parameter which seems to be interested for my problem, because I could set it up to something like (2,3) for a input feature of shape (batch_size, nFrames, nFreqBins, nDim) and hope attention will be applied on the wanted dimensions. However I don't understand how it works since it's different from the original Transformer paper, and I don't find any relevant paper addressing self-attention in several dimensions in the same manner.

Also the source code doesn't help, the algorithm is split into several sub-modules which are not self-explanatory to me.

Any insights would be precious!

Thanks a lot

i.e., I need to know, the best audio compression algorthims.

I am conducting research on automated audio editing, by artificial intelligence, to remove oratory addictions, such as stuttering, repetition of sounds like "ahaa", "hummm", and other recording noises that affect the sound quality of the audio.

I ask you to indicate, please, articles and other bibliographic materials on the topic, in addition to any other suggestions that you have.

Does anyone have suggestions on software that has been particularly helpful in transcribing and analyzing data recorded during focus groups? We have some money from a grant that can be used to purchase licenses. Any insight would be helpful. Thank you.

Hello,

I have been working on acoustic echo cancellation while following the research paper :

Since I am working on real-time audio data so my problem is as follows:

Problem Statement:

------------------------------

| |

| H E L L O |

------------------------------

is being played by phone and now its echo is being recorded in a Near-End packet. Now the cases arise here are that this could be recorded as:1

------------------------------

| H E L L O |

------------------------------

Hello completely recorded in one packet.

2. ------------------------------ ------------------------------

| | | |

| H E | | L L O |

------------------------------ ------------------------------

Distributed in two Near-end packets

3. ------------------------------ ------------------------------

| | | |

| H | | E L L O |

------------------------------ ------------------------------

and so on random distribution of far-end audio between multiple chunks of near-end audio.

Now, I want to detect echo and perform cancellation. That can be done if I get an accurate chunk of far-end whose echo is in the near end chunk. Right now I am making overlapped chunks with the shift of 1 sample equivalent to 0.020833 ms of data. But this is quite computationally over expensive.

So 2 questions arise here:

I hope my question will be cleared. I tried to explain it yet keep it concise.

Any help will be appreciated.

Regards,

Khubaib Ahmad

Hello,

I have been working on the decorrelation of audio signals while following this paper :

" "

So far I have generated impulse responses in such a way that magnitude is 1 in all frequency spectrum, while random phase generation between -π to π. I correlated these signals and I am getting the required correlation.

Now moving on, when I convolve this impulse response with my audio signal, results in the case of decorrelation are good but the audio becomes noisy and distorted. I am attaching the reference wav file and and decorrelated wav file.

Any help will be appreciated.

Regards,

Khubaib Ahmad

Hi!

I tried JotForms, but the only audio files I could insert were SoundCloud links, which is not good at all as they have to be public to work.

This is for my thesis, which investigates the effects of an ASR-based application on the intelligibility of Brazilian speakers of English.

Thank you! I hope I didn't miss an easy/obvious solution for my problem.

Hi,

I am transcribing a lot of audio interviews. Currently, I am using Windows Media Player and if I have it hit pause and go back to clarify what was said I have to use the slider down the bottom which often takes me too far. Just wondering what software others are using which has a back key option that will allow you to go back say 10 or 15 seconds per hit. This will save me a lot of time.

Thanks in advance

Hi,

I have been working on multi-loudspeaker and single mic acoustic echo canceller ( more than a typical stereophonic echo canceller). I have researched and came to know that we have to decorrelate the signals in order to correctly identify the estimated echo signal (i.e replicate impulse response). So, I want to know if there are any decorrelation techniques for let's say N number of loudspeakers?

Please share the link if possible.

Regards,

Khubaib Ahmad

I want to convert audio signal(live recorded using microphone) to digital which I can transmit that digital signal over Bluetooth. I have designed a signal conditioning circuit which has a series of pre-amplifier, filter and DC level shifter, output of signal conditioning circuit is to convert in to digital form. For this conversion I want to use microcontroller. And also suggest Bluetooth module for same.

I aim to take a raw audio file as input. And my final objective is to convert that audio into an, unique for each audio, ID. Is there any python library to do it? One which takes audio as an input.

Or One which can at least convert it to something from where I can further convert it to unique IDs?

Thanks in advance.

Hi all,

I'm currently undertaking a research project for my dissertation and will be using Audio Moth to recording vocalizations from Bleeding Heart Doves. Their calls are relatively low at 500 htz. I'm looking for any software suggestions that might be useful in analyzing these recordings as well as isolating potential vocalizations from these birds.

Any suggestion is a great help as I don't know where to start.

Thanks!

Hello,

I wanted to know that related to an audio signal which has Amplitude, Frequency, and Phase as key characteristics. Do MFCC coefficients depend on them? Are there any other factors on which MFCC coefficients depend?

Regards,

Khubaib

Hi everyone,

I need to plan an online experiment in which each participant should watch a series of screens each containing an image (the screens/images must appear in a randomized order). During the whole series of screens, an audio file should be played, it should begin at the first image and it should end at the end of the session.

I have a Qualtrics account, but I'm not able to implement this kind of procedure. In general, as I build a page with the audio player, the audio won't be playing anymore as soon as the next screen is on. On the contrary, I need the audio to be playing in the background during the whole presentation.

Could I achieve my aim by programming something in Python / Java / Node JS / HTML? Or should I change software? Any suggestions?

thanks in advance for any help

all the best,

Alessandro

Dear Colleagues, please suggest which is the best and user friendly open source software for audio signal analysis with most of the Scientific tools to audio signal analysis.

Thanks and Regards

N Das

Hello everyone!

I am working with a comparatively small audio dataset for classification task. I was searching for a means to ensure robust performance and thus, came across the following paper [1] that performed test-time augmentation on the test set. The test-time augmentation includes four procedures: augmentation, prediction, dis-augmentation and merging as follows:

First, the test images are augmented (rotation, flip) as done on the training set. Prediction is performed on both the original and the augmented images, then they revert the transformation on the obtained predictions (dis-augmentation). Merging can be done by employing the majority voting criterion with several additional steps.

I am confused regarding the dis-augmentation and the merging steps in case of time-frequency representation of audio signals (spectrograms, scalograms). Is this method applicable for time-frequency representation of audio signals? If any of you can enlighten me in this regard, that will be really helpful. Thanks in advance!

[1] Moshkov, N., Mathe, B., Kertesz-Farkas, A. et al. Test-time augmentation for deep learning-based cell segmentation on microscopy images. Sci Rep 10, 5068 (2020).

Hi all,

This is my first time posting to Research Gate, I often look through posts for similar research questions I have of my own. I am in a Research Methods grad course and I am suppose to create a statistical hypothesis and choose a testing method for my study. I have developed this problem statement and research questions:

The problem to be addressed is, how to effectively deliver take-over-requests (TOR) to get the quickest response time from a driver.

Overarching research questions to this problem statement is:

1) What type of take over request (TOR) is warrants the most efficient response time by driver?

2) How do response times between elderly drivers and young drivers differ?

3) Do elderly drivers respond better to certain stimuluses?

I want to test multiple TOR methods such as: Visual/audio, audio/haptic, audio, haptic and visual against two categorical age groups (young and old drivers), with my dependent variable being time.

Does a Two-way ANOVA sound appropriate for this? I've asked two different professors, one gave me a cryptic, you can't do that, type answer...and another one gave me an answer that i'm still uncertain of. Please let me know if i'm headed in the correct direction with this of if there is a better way.

Thank you.

Al-Hussein bin Talal University- Ma’an-Jordan, decided to adopt a system that makes providing a complete audio and video recording of the conduct of discussions of all undergraduate and doctoral dissertations in the university compulsory as a positive measure that enhances quality, transparency and confidence and reflects a clear picture of the quality and sometimes seriousness of the research work and student capabilities and benefits the rest of the students in the process of preparing for their thesis discussions and increases the knowledge content of university libraries. Al-Hussein bin Talal University invites world universities and the scientific community to express an opinion on the pros or cons of this procedure and accreditation when convinced of its usefulness. Najib Abou Karaki / President of Al-Hussein Bin Talal University Juin 2020.

It is a well known fact that in audio reconstruction magnitude and phase both information is required for a high quality synthesis. Many reasearch are focused on converting audio into spectrograms and then use only magnitude (2D image) as an input to GAN network, which generates a similar spectrogram (only magnitude) and the phase is approximated at the end using differnt techniques such as Griffin Lim.

I have been searching for the resarch who has used both magnitude and phase image in GAN network. But to my surprise, I don't find any work that use both Magnitude and phase as an input to GAN. How come it is not been done or I am not able to search?

The audio recognition is one of the deep learning application

For fast training , the audio signal is divided into set of rows before the feature extraction and running the deep learning model are done

How we can do this division in a python code ??

I am trying to build a joint classifier for Bimodal Sentiment Analysis which takes two modalities(audio and video files) as inputs. Any suggestions, how can I concatenate the below audio and video features to train a CNN based deep learning models?

Audio features:

X_aud = np.asarray(aud_data)

y_aud = np.asarray(aud_labels)

X_aud.shape, y_aud.shape

((1440, 40), (1440,))

Video features:

X_img = np.asarray(image_data)

y_img = np.asarray(img_labels)

X_img.shape, y_img.shape

((11275, 256, 512, 3), (11275,))

Any help would be highly appreciated. Thanks In Advance!

Hi All,

I have an audio database consisting of various types of signals and I'm planning to extract features from the audio signal. So I would like to know whether it's a good idea to extract basic audio features (eg MFCC, Energy ) from the audio signal with a large window (Let's say 5s width 1s overlap) rather than using conventional small frame size (in ms). I know that the audio signal exhibits homogeneous behavior in a 5s duration.

Thanks in advance

Hi,

We at Tata Medical Center, Radiation Oncology Department have been developing an online software that allows us to collect patient-reported outcomes. The software allows users to set up and deliver multiple forms and questionnaires and also is easily amenable to be translated into the Indian Language and delivered accordingly. Furthermore to improve the experience of filling the questionnaire the software supports the integration of translated media like audio and video.

We need some help with user experience testing and would be really obliged if you can spare 15 minutes of your time. We would appreciate if you can ask someone in your family so is not much computer savvy to do it. Please reply to this message if you are interested and we will send you the details.

Please note that the current test checks how well a "layperson" can navigate to the software, find the form to fill and then fill it. Subsequently, a few questions will be asked on how the user felt the software performed and how difficult/easy it was. This user experience testing will essentially allow us to understand the "choke points" where a patient can fail when the software is actually deployed for clinical use.

We will be sending the instructions in a word document if you request for it.

We will acknowledge all those who participate in our system as well as in the initial publication.

Thanks

I'm looking for recommendations on software. I want to have 10-12 undergraduates at my college listen to 18+ one minute audio files of college-level lectures. Learners need to rate each file for comprehensibility and name the main topic in a few words. Then they need to rank the audio files from most to least comprehensible. Because of Covid-19 fears, participants will need to work individually at a computer in a language learning lab with little to no supervision. I want them to be able to enter their responses on the computer, and they need to be able to listen to the audio files as many times as they like, in any order they like. Suggestions??

I conducted a qualitative research and recorded the interview as audio clips for each respondent. How we analyse the audio based data using R software?

This is quite common in NVIVO and Atlas.ti. but I want to use R software.

Kindly guide me please.

Thanks and regards.

For an upcoming research project I will have audio files of interviews conducted in Spanish. I am looking for a company that can transcribe and translate these interviews - resulting in English transcripts. What companies have others used for this? Confidentiality and relatively low cost are important.