Speech/music discrimination using perceptual feature

Ghosal, Arijit; Dutta, Suchibrota

doi:10.1201/9781315375021-15

Cited by 5 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding datasets, both Scheirer and Slaney (S&S) and GTZAN databases had been extensively used by researchers for evaluation [1,5,15,16,19,21]. However, some of the work used their own created database [2,7,22].…”

Section: Related Workmentioning

confidence: 99%

Hilbert spectrum based features for speech/music classification

2022

View full text Add to dashboard Cite

Automatic Speech/Music classification uses different signal processing techniques to categorize multimedia content into different classes. The proposed work explores Hilbert Spectrum (HS) obtained from different AM-FM components of an audio signal, also called Intrinsic Mode Functions (IMFs) to classify an incoming audio signal into speech/music signal. The HS is a twodimensional representation of instantaneous energies (IE) and instantaneous frequencies (IF) obtained using Hilbert Transform of the IMFs. This HS is further processed using Mel-filter bank and Discrete Cosine Transform (DCT) to generate novel IF and Instantaneous Amplitude (IA) based cepstral features. Validations of the results were done using three databases-Slaney Database, GTZAN and MUSAN database. To evaluate the general applicability of the proposed features, extensive experiments were conducted on different combination of audio files from S&S, GTZAN and MUSAN database and promising results are achieved. Finally, performance of the system is compared with performance of existing cepstral features and previous works in this domain.

show abstract

Section: Related Workmentioning

confidence: 99%

Hilbert spectrum based features for speech/music classification

2022

View full text Add to dashboard Cite

show abstract

“…Due to massive amounts of this data it is impossible to generate classes, la-bels, descriptions, transcriptions manually, or many of the main tasks that are required to take advantage of the information [2]. To answer the demands for handling the data, a field of research, known as audio content analysis (ACA), or machine listening, has recently emerged [1].…”

Section: Introductionmentioning

confidence: 99%

“…Among the main challenges in performing speech/music classification is to obtain high accuracy with characteristics of short-time delay and low complexity [5], due to the vast amount of information that need to be processed and its efficient utilization in the applications. For discriminating the audio content in categories such as music and speech, data two successive stages have to be performed: i) the extraction of features from the input audio data, and ii) the classification of the data into established categories [2].…”

Section: Introductionmentioning

confidence: 99%

Comparison of four classifiers for speech-music discrimination: a first case study for costa rican radio broadcasting

Sánchez-Solís¹,

Coto-Jiménez²

2022

View full text Add to dashboard Cite

During the past decades, a vast amount of audio data has be- come available in most languages and regions of the world. The efficient organization and manipulation of this data are important for tasks such as data classification, searching for information, diarization among many others, but also can be relevant for building corpora for training models for automatic speech recognition or building speech synthesis systems. Several of those tasks require extensive testing and data for specific languages and accents, especially when the development of communication systems with machines is a goal. In this work, we explore the application of several classifiers for the task of discriminating speech and music in Costa Rican radio broadcast. This discrimination is a first task in the exploration of a large corpus, to determine whether or not the available information is useful for particular research areas. The main contribution of this exploratory work is the general procedure and selection of algorithms for the Costa Rican radio corpus, which can lead to the extensive use of this source of data in many own applications and systems.

show abstract