Acoustic Event Classification Using Spectrogram Features

Mulimani, Manjunath; Koolagudi, Shashidhar G.

doi:10.1109/tencon.2018.8650444

Cited by 20 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the task of classifying audio events has often been addressed in the speech technology literature. In particular, the speech activity detection task [8] or the acoustic event detection problem [9,10] are similar to the voice type classification task we address in this paper.…”

Section: Introduction and Related Workmentioning

confidence: 99%

An Open-Source Voice Type Classifier for Child-Centered Daylong Recordings

Lavechin¹,

Bousbib²,

Bredin³

et al. 2020

Interspeech 2020

View full text Add to dashboard Cite

Spontaneous conversations in real-world settings such as those found in child-centered recordings have been shown to be amongst the most challenging audio files to process. Nevertheless, building speech processing models handling such a wide variety of conditions would be particularly useful for language acquisition studies in which researchers are interested in the quantity and quality of the speech that children hear and produce, as well as for early diagnosis and measuring effects of remediation. In this paper, we present our approach to designing an open-source neural network to classify audio segments into vocalizations produced by the child wearing the recording device, vocalizations produced by other children, adult male speech, and adult female speech. To this end, we gathered diverse child-centered corpora which sums up to a total of 260 hours of recordings and covers 10 languages. Our model can be used as input for downstream tasks such as estimating the number of words produced by adult speakers, or the number of linguistic units produced by children. Our architecture combines SincNet filters with a stack of recurrent layers and outperforms by a large margin the state-of-the-art system, the Language ENvironment Analysis (LENA) that has been used in numerous child language studies.

show abstract

Section: Introduction and Related Workmentioning

confidence: 99%

An Open-Source Voice Type Classifier for Child-Centered Daylong Recordings

Lavechin¹,

Bousbib²,

Bredin³

et al. 2020

Interspeech 2020

View full text Add to dashboard Cite

show abstract

“…Research on audio processing has been focused significantly on the use of a single representation of the audio. Among the most common representations are the use of spectrograms (Mulimani & Koolagudi, 2018;Zeng et al, 2019;Sarthak et al, 2019), and MFCCs (Lee & Jang, 2018;Ahmad et al, 2015), which can be competitive depending on the task and the dataset used, and, in general, both can obtain similar results (Meghanani et al, 2021).…”

Section: State Of the Artmentioning

confidence: 99%

MeWEHV: Mel and Wave Embeddings for Human Voice Tasks

Vasco-Carofilis¹,

Fernández-Robles²,

Alegre³

et al. 2022

Preprint

View full text Add to dashboard Cite

A recent trend in speech processing is the use of embeddings created through machine learning models trained on a specific task with large datasets. By leveraging the knowledge already acquired, these models can be reused in new tasks where the amount of available data is small. This paper proposes a pipeline to create a new model, called Mel and Wave Embeddings for Human Voice Tasks (MeWEHV), capable of generating robust embeddings for speech processing. MeWEHV combines the embeddings generated by a pre-trained raw audio waveform encoder model, and deep features extracted from Mel Frequency Cepstral Coefficients (MFCCs) using Convolutional Neural Networks (CNNs).We evaluate the performance of MeWEHV on three tasks: speaker, language, and accent identification. For the first one, we use the VoxCeleb1 dataset and present YouSpeakers204, a new and publicly available dataset for English speaker identification that contains 19607 audio clips from 204 persons speaking in six different accents, allowing other researchers to work with a very balanced dataset, and to create new models that are robust to multiple accents. For evaluating the language identification task, we use the VoxForge and Common Language datasets. Finally, for accent identification, we use the Latin American

show abstract

“…In the paper [35] This [20]paper, it has described that Support vector machine (SVM) has lot of outstanding ability, especially in classification problems. Its basic design philosophy is to maximize the classification boundaries and its basic purpose is to maximize the hyper-plan.…”

Section: Related Workmentioning

confidence: 99%

Predicting Effectiveness of Marketing through Analyzing Emotional Context in Advertisement using Deep Learning

Arafat¹,

Islam²,

Rafi³

et al. 2021

2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)

View full text Add to dashboard Cite

In this modern age, marketing strategy is becoming a new challenge. Not only the global market but also people's choices are shifting to catch the attention of buyers. Also, based on consumer's choice organizations are bringing changes in their marketing policy to increase the chances of their product selling rate. Basically, to promote their products and grab buyer's attention they are promoting advertisements on every media platform. But they are not aware of the effectiveness of marketing and which emotional states are needed more and which are not needed much. Therefore, we lead this study to recognize a successful advertisement and identify the rate of the emotional states which make good impact in people mind to purchase the product. Using deep learning and supervised machine learning algorithms as well as feature extraction methods for instance, LSTM-RNN, SVM, XGBOOST, Naïve Bayes, Multiple Linear Regression, MFCC, Zero-Crossing Rate, Power Spectral Density, we find out and evaluate the rate of the emotional states to figure out the liking and purchase intent which makes an advertisement successful.

show abstract

Acoustic Event Classification Using Spectrogram Features

Cited by 20 publications

References 12 publications

An Open-Source Voice Type Classifier for Child-Centered Daylong Recordings

An Open-Source Voice Type Classifier for Child-Centered Daylong Recordings

MeWEHV: Mel and Wave Embeddings for Human Voice Tasks

Predicting Effectiveness of Marketing through Analyzing Emotional Context in Advertisement using Deep Learning

Contact Info

Product

Resources

About