Singing voice detection in polyphonic music using predominant pitch

Rao, Vishweshwara; Ramakrishnan, S.; Rao, Preeti

doi:10.21437/interspeech.2009-330

Cited by 12 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To increase robustness to such accompaniment we then enhanced the feature by taking into account the temporal variation of the pitch contour, in order to exploit voice-pitch instability (see Section 2), as opposed to keyed-instrument pitch stability. Classification results using this enhanced feature did not show any degradation even in the presence of loud pitched instruments [23].…”

Section: Sung Segment Detectionmentioning

confidence: 87%

Musical information extraction from the singing voice

Rao¹

2009

National Conference on Signal and Image Processing Applications

View full text Add to dashboard Cite

Music information retrieval is currently an active research area that addresses the extraction of musically important information from audio signals, and the applications of such information. The extracted information can be used for search and retrieval of music in recommendation systems, or to aid musicological studies or even in music learning. Sophisticated signal processing techniques are applied to convert low-level acoustic signal properties to musical attributes which are further embedded in a rulebased or statistical classification framework to link with high-level descriptions such as melody, genre, mood and artist type. Vocal music comprises a large and interesting category of music where the lead instrument is the singing voice. The singing voice is more versatile than many musical instruments and therefore poses interesting challenges to information retrieval systems. In this paper, we provide a brief overview of research in vocal music processing followed by a description of related work at IIT Bombay leading to the development of an interface for melody detection of singing voice in polyphony.

show abstract

Section: Sung Segment Detectionmentioning

confidence: 87%

Musical information extraction from the singing voice

Rao¹

2009

National Conference on Signal and Image Processing Applications

View full text Add to dashboard Cite

show abstract

“…People's life needs are the starting point of scientific research, and science and technology are the driving force that promotes the continuous progress of mankind (Powers 2011). The literature shows that as people pay more and more attention to the mobile Internet of Things, smartphone operating systems and audio and video communication standards have emerged one after another (Rao et al 2008).…”

Section: Related Workmentioning

confidence: 99%

Application of Audio Technology of Internet of Things Based on Parallel Storage System in Music Classroom

Jiang

2023

Preprint

View full text Add to dashboard Cite

Hard disk not only has powerful storage capacity, but also has highly intelligent interface and convenient application design. In daily life, hard disk is a very suitable tool for data collection and storage. The performance of hard disk is better when the number of samples is not too many, the sampling rate is low, and the number of sampling paths is small. However, when faced with some complex problems with high sampling rate and multiple paths, high-speed data storage will face greater difficulties. Therefore, this paper introduces a parallel storage system, and discusses the basic structure and the implementation of the system the factors that affect the storage rate, the specific structure of the data acquisition system in the system, which is subdivided into the structure of the power supply, data acquisition, caching and sorting and so on. With the support of parallel storage system, this paper summarizes some basic characteristics of audio, and focuses on the decisive role of hard disk in audio interactive system. In the process of research, it is found that the hardware system based on parallel storage system has many advantages, such as low consumption, small volume, high performance and low cost, which can achieve the research goal well. In recent years, the Internet of things has been widely used in many fields. Scientists have long explored the application of the Internet of things technology in the construction of contemporary mobile multimedia audio system, so that the multimedia video communication system can achieve intelligent development, and at the same time to realize its performance optimization, the price of the Internet of things audio technology can be reduced. In this paper, combined with the advantages of parallel storage system, the application of Internet of things audio technology in music classroom will be discussed to improve the efficiency of music teaching and students' music literacy.

show abstract

“…Such distinction mistakes lead to plenty of Instrumental being labelled as Song. Aerophones and fretless stringed instruments, for example, are known to produce similar pitch modulations as the human voice [53,54]. This study focuses on improving Instrumental detection in musical databases because the current state-of-the-art algorithms are unable to generate a faultless playlist with the tag Instrumental [55,56].…”

Section: Introductionmentioning

confidence: 99%

Toward Faultless Content-Based Playlists Generation for Instrumentals

Bayle¹,

Robine²,

Hanna³

2017

Preprint

View full text Add to dashboard Cite

This study deals with content-based musical playlists generation focused on Songs and Instrumentals. Automatic playlist generation relies on collaborative filtering and autotagging algorithms. Autotagging can solve the cold start issue and popularity bias that are critical in music recommender systems. However, autotagging remains to be improved and cannot generate satisfying music playlists. In this paper, we suggest improvements toward better autotagging-generated playlists compared to state-of-the-art. To assess our method, we focus on the Song and Instrumental tags. Song and Instrumental are two objective and opposite tags that are under-studied compared to genres or moods, which are subjective and multi-modal tags. In this paper, we consider an industrial real-world musical database that is unevenly distributed between Songs and Instrumentals and bigger than databases used in previous studies. We set up three incremental experiments to enhance automatic playlist generation. Our suggested approach generates an Instrumental playlist with up to three times less false positives than cutting edge methods. Moreover, we provide a design of experiment framework to foster research on Songs and Instrumentals. We give insight on how to improve further the quality of generated playlists and to extend our methods to other musical tags. Furthermore, we provide the source code to guarantee reproducible research.

show abstract

Singing voice detection in polyphonic music using predominant pitch

Cited by 12 publications

References 9 publications

Musical information extraction from the singing voice

Musical information extraction from the singing voice

Application of Audio Technology of Internet of Things Based on Parallel Storage System in Music Classroom

Toward Faultless Content-Based Playlists Generation for Instrumentals

Contact Info

Product

Resources

About