Artificially Synthesising Data for Audio Classification and Segmentation to Improve Speech and Music Detection in Radio Broadcast

02/19/2021
by   Satvik Venkatesh, et al.
6

Segmenting audio into homogeneous sections such as music and speech helps us understand the content of audio. It is useful as a pre-processing step to index, store, and modify audio recordings, radio broadcasts and TV programmes. Deep learning models for segmentation are generally trained on copyrighted material, which cannot be shared. Annotating these datasets is time-consuming and expensive and therefore, it significantly slows down research progress. In this study, we present a novel procedure that artificially synthesises data that resembles radio signals. We replicate the workflow of a radio DJ in mixing audio and investigate parameters like fade curves and audio ducking. We trained a Convolutional Recurrent Neural Network (CRNN) on this synthesised data and outperformed state-of-the-art algorithms for music-speech detection. This paper demonstrates the data synthesis procedure as a highly effective technique to generate large datasets to train deep neural networks for audio segmentation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/30/2021

Unsupervised Learning of Deep Features for Music Segmentation

Music segmentation refers to the dual problem of identifying boundaries ...
research
11/25/2022

Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?

With the similarity between music and speech synthesis from symbolic inp...
research
09/01/2021

You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection

Audio segmentation and sound event detection are crucial topics in machi...
research
12/01/2018

SwishNet: A Fast Convolutional Neural Network for Speech, Music and Noise Classification and Segmentation

Speech, Music and Noise classification/segmentation is an important prep...
research
04/15/2018

Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing

Spoken content processing (such as retrieval and browsing) is maturing, ...
research
07/15/2020

Content-based Recommendations for Radio Stations with Deep Learned Audio Fingerprints

The world of linear radio broadcasting is characterized by a wide variet...
research
02/12/2020

Improving automated segmentation of radio shows with audio embeddings

Audio features have been proven useful for increasing the performance of...

Please sign up or login with your details

Forgot password? Click here to reset