Delayed Decision-making in Real-time Beatbox Percussion Classification

Stowell, Dan; Plumbley, Mark D.

doi:10.1080/09298215.2010.512979

Cited by 16 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sinyor et al (2005) extracted 24 acoustic features from recordings of five imitated percussion effects, for the purpose of automatic categorization. Stowell and Plumbley (2010) examined real-time classification accuracy of an annotated dataset of 14 sounds produced by expert beatboxers. Acoustic feature analysis of vocal percussion imitation by non-beatboxers has also been conducted in music retrieval systems research (e.g., Kapur et al, 2004).…”

Section: Introductionmentioning

confidence: 99%

Paralinguistic mechanisms of production in human “beatboxing”: A real-time magnetic resonance imaging study

Proctor

Bresch

Byrd

et al. 2013

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Real-time magnetic resonance imaging (rtMRI) was used to examine mechanisms of sound production by an American male beatbox artist. rtMRI was found to be a useful modality with which to study this form of sound production, providing a global dynamic view of the midsagittal vocal tract at frame rates sufficient to observe the movement and coordination of critical articulators. The subject's repertoire included percussion elements generated using a wide range of articulatory and airstream mechanisms. Many of the same mechanisms observed in human speech production were exploited for musical effect, including patterns of articulation that do not occur in the phonologies of the artist's native languages: ejectives and clicks. The data offer insights into the paralinguistic use of phonetic primitives and the ways in which they are coordinated in this style of musical performance. A unified formalism for describing both musical and phonetic dimensions of human vocal percussion performance is proposed. Audio and video data illustrating production and orchestration of beatboxing sound effects are provided in a companion annotated corpus.

show abstract

Section: Introductionmentioning

confidence: 99%

Paralinguistic mechanisms of production in human “beatboxing”: A real-time magnetic resonance imaging study

Proctor

Bresch

Byrd

et al. 2013

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

show abstract

“…These sounds are often perceived as overlapping (occurring in synchrony) in time. The majority of beatboxing sounds imitate percussion instruments like drums and cymbals yet are also seen as similar to speech sounds and can be described using symbols from the International Phonetic Alphabet (IPA; Stowell and Plumbley, 2008;Stowell and Plumbley, 2010;Proctor et al, 2013) 1 or with the use of characters from a standard English computer keyboard as in the SBN (Splinter and TyTe, 2002).…”

Section: Beatboxingmentioning

confidence: 99%

Using Beatboxing for Creative Rehabilitation After Laryngectomy: Experiences From a Public Engagement Project

et al. 2020

View full text Add to dashboard Cite

Laryngectomy is the surgical removal of the larynx (voice box), usually performed in patients with advanced stages of throat cancer. The psychosocial impact of losing the voice is significant, affecting a person's professional and social life in a devastating way, and a proportion of this patient group subsequently must overcome depression (22-30%) and social isolation (40%). The profound changes to anatomical structures involved in voicing and articulation, as a result of surgery, radiotherapy or chemotherapy (separately or in combination with one another), introduce challenges faced in speech rehabilitation and voice production that complicate social reintegration and quality of life. After laryngectomy, breathing, voicing, articulation and tongue movement are major components in restoring communication. Regular exercise of the chest, neck and oropharyngeal muscles, in particular, is important in controlling these components and keeping the involved structures supple. It is, however, a difficult task for a speech therapist to keep the patient engaged and motivated to practice these exercises. We have adopted a multidisciplinary approach to explore the use of basic beatboxing techniques to create a wide variety of exercises that are seen as fun and interactive and that maximize the use of the structures important in alaryngeal phonation. We herein report on our empirical work in developing patients' skills, particularly relating to voiced and unvoiced consonants to improve intelligibility. In collaboration with a professional beatboxing performer, we produced instructional online video materials to support patients working on their own and/or with support from speech therapists. Although the present paper is focused predominantly on introducing the structure of the conducted workshops, the rationale for their design and the final public engagement performance, we also include feedback from participants to commence the critical discourse about

show abstract

“…In most cases, a modest vocal percussion dataset is recorded for evaluation purposes, which could be oriented to general rhythmic vocal percussion [8] [21] [19] [7] or just beatboxing [11] [22]. Some of the mentioned work target user-specific vocal percussion analysis rather than general methods that could work for everyone, as vocal imitation styles seem to change significantly from person to person [9] [19].…”

Section: Previous Workmentioning

confidence: 99%

“…There are four widely adopted vocal percussion datasets in the public domain. The first one is the Beatbox dataset by Stowell et al [22]. It gathered experienced beatboxers to record 14 audio files (one per participant) with a mean duration of 47 seconds that resulted in a total of 7460 annotated utterances.…”

Section: Previous Workmentioning

confidence: 99%

A New Dataset for Amateur Vocal Percussion Analysis

Delgado

McDonald

et al. 2019

Proceedings of the 14th International Audio Mostly Conference: A Journey in Sound

View full text Add to dashboard Cite

The imitation of percussive instruments via the human voice is a natural way for us to communicate rhythmic ideas and, for this reason, it attracts the interest of music makers. Specifically, the automatic mapping of these vocal imitations to their emulated instruments would allow creators to realistically prototype rhythms in a faster way. The contribution of this study is twofold. Firstly, a new Amateur Vocal Percussion (AVP) dataset is introduced to investigate how people with little or no experience in beatboxing approach the task of vocal percussion. The end-goal of this analysis is that of helping mapping algorithms to better generalise between subjects and achieve higher performances. The dataset comprises a total of 9780 utterances recorded by 28 participants with fully annotated onsets and labels (kick drum, snare drum, closed hi-hat and opened hi-hat). Lastly, we conducted baseline experiments on audio onset detection with the recorded dataset, comparing the performance of four state-of-the-art algorithms in a vocal percussion context.

show abstract

Delayed Decision-making in Real-time Beatbox Percussion Classification

Cited by 16 publications

References 11 publications

Paralinguistic mechanisms of production in human “beatboxing”: A real-time magnetic resonance imaging study

Paralinguistic mechanisms of production in human “beatboxing”: A real-time magnetic resonance imaging study

Using Beatboxing for Creative Rehabilitation After Laryngectomy: Experiences From a Public Engagement Project

A New Dataset for Amateur Vocal Percussion Analysis

Contact Info

Product

Resources

About