scholarly journals Probabilistic Segmentation of Folk Music Recordings

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Ciril Bohak ◽  
Matija Marolt
Keyword(s):  
Folk Music ◽  
Distance Measure ◽  
Automatic Segmentation ◽  
Segment Length ◽  
Programming Approach ◽  
Commercial Music ◽  
Dynamic Programming Approach ◽  
Field Recordings ◽  
Dynamic Time ◽  
Music Recordings

The paper presents a novel method for automatic segmentation of folk music field recordings. The method is based on a distance measure that uses dynamic time warping to cope with tempo variations and a dynamic programming approach to handle pitch drifting for finding similarities and estimating the length of repeating segment. A probabilistic framework based on HMM is used to find segment boundaries, searching for optimal match between the expected segment length, between-segment similarities, and likely locations of segment beginnings. Evaluation of several current state-of-the-art approaches for segmentation of commercial music is presented and their weaknesses when dealing with folk music are exposed, such as intolerance to pitch drift and variable tempo. The proposed method is evaluated and its performance analyzed on a collection of 206 folk songs of different ensemble types: solo, two- and three-voiced, choir, instrumental, and instrumental with singing. It outperforms current commercial music segmentation methods for noninstrumental music and is on a par with the best for instrumental recordings. The method is also comparable to a more specialized method for segmentation of solo singing folk music recordings.

From here

2019 ◽  
Vol 18 (4) ◽  
pp. 598-616
Author(s):  
Matthew Ord
Keyword(s):  
Folk Music ◽  
Sound Studies ◽  
Music Culture ◽  
Field Recordings ◽  
Multimodal Analysis ◽  
Field Recording ◽  
English Identity ◽  
Construction Of Place ◽  
Music Recordings ◽  
Insight Into

Abstract This article considers the sonic construction of place in English folk music recordings. Recent shifts in the political context have stimulated renewed interest in English identity within folk music culture. Symbolic struggles over folk’s political significance highlight both the contested nature of English identity and music’s semantic ambiguity, with texts being interpolated into discourses of both ethnic purity and multiculturalism. Following research in popular music, sound studies and multimodal communication this article explores the use of field recording to explore questions of place and Englishness in the work of contemporary folk artists. A multimodal analysis of Stick in the Wheel’s From Here: English Folk Field Recordings (2017) suggests that a multimodal approach to musical texts that attends to the semantic affordances of sound recording can provide insight into folk music’s role in debates over the nature of English identity.

Dynamic Incentive Mechanism for Delivery Slot Management in E-Commerce Attended Home Delivery

2020 ◽  
Vol 54 (3) ◽  
pp. 567-587 ◽  
Author(s):  
Albert Vinsensius ◽  
Yuan Wang ◽  
Ek Peng Chew ◽  
Loo Hay Lee
Keyword(s):  
Free Choice ◽  
Time Slot ◽  
Incentive Mechanism ◽  
Time Windows ◽  
Home Delivery ◽  
Programming Approach ◽  
Dynamic Programming Approach ◽  
Dynamic Time ◽  
High Level ◽  
Selection Of

In attended home delivery, challenges arise in practice because of the short strict time windows, stochastic customer requests, and varying customers’ preferences for delivery slots. In this study, we focus on integrating dynamic time slot incentives and order delivery with the intention of reducing overall delivery cost and improving profitability. The proposed incentive mechanism is able to exploit the variability in the marginal fulfillment cost of an order and the customers’ preferences to influence the customers’ selection of delivery slots. We present an approximate dynamic programming approach to estimate the marginal fulfillment cost using the operational vehicle routing cost while accounting for future orders. We demonstrate that the proposed incentive mechanism can achieve a high level of savings (of up to 70%) with respect to the benchmark customer-free-choice scenario. It is also noted that the proposed mechanism effectively exploits higher order density and vehicle availability to achieve a higher level of savings.

scholarly journals Automatic Segmentation of Ethnomusicological Field Recordings

2019 ◽  
Vol 9 (3) ◽  
pp. 439
Author(s):  
Matija Marolt ◽  
Ciril Bohak ◽  
Alenka Kavčič ◽  
Matevž Pesek
Keyword(s):  
Folk Music ◽  
Classification Accuracy ◽  
Background Noise ◽  
Network Architecture ◽  
Automatic Segmentation ◽  
Probabilistic Approach ◽  
Segmentation Method ◽  
Field Recordings ◽  
Deep Networks ◽  
Feature Based

The article presents a method for segmentation of ethnomusicological field recordings. Field recordings are integral documents of folk music performances captured in the field, and typically contain performances, intertwined with interviews and commentaries. As these are live recordings, captured in non-ideal conditions, they usually contain significant background noise. We present a segmentation method that segments field recordings into individual units labelled as speech, solo singing, choir singing, and instrumentals. Classification is based on convolutional deep networks, and is augmented with a probabilistic approach for segmentation. We describe the dataset gathered for the task and the tools developed for gathering the reference annotations. We outline a deep network architecture based on residual modules for labelling short audio segments and compare it to the more standard feature based approaches, where an improvement in classification accuracy of over 10% was obtained. We also present the SeFiRe segmentation tool that incorporates the presented segmentation method.

Sign in / Sign up

Export Citation Format

Share Document