Voice Complaints, Vocal and Non-vocal Behaviours Among Beatboxers - A Preliminary Study.

INTRODUCTION: Beat boxing is an art of vocal percussion, which involves imitating musical instruments using oral structures. They use techniques like click rolls and trills which involves the usage of entire vocal apparatus for a longer period making use of the human body as a versatile physical instrument to recreate musical beats as well as vocal expressions. The aim and objectives of the present study were to develop a questionnaire and to profile the voice complaints, vocal and non-vocal habits among beatboxers in India. METHOD: A cross-sectional study design was used to profile the voice complaints, vocal and non-vocal habits among beatboxers in India. Phase I involved questionnaire development and validation. Phase II involved data collection and analysis. RESULTS: Thirty-seven beatboxers from India participated of which 70.27% were trained. The beatboxers reported of beatboxing musical instruments such as; flute/trumpet, harmonica, guitar, and drums. The commonly practiced vocal techniques was bass (22.07%). Most common vocal complaints included vocal fatigue after long usage of voice (72.97%) and breathing difficulty after performance (86.49%). Further, 76.38% reported of using loud voice during performances. Poor non-vocal habits such as muscle tension during beatboxing (56.76%), breathing difficulty during beatboxing (45.94%). Two most common good non-vocal habits included food intake on time (78.38%) and use of relaxation techniques (72.97%) prior to performance. CONCLUSION: The present study was a preliminary attempt to profile the voice complaints, vocal and non-vocal habits observed in this upcoming profession of beatboxing. Further, studies are needed to explore the voice of these professionals from a multidimensional perspective.

A Distributional Perspective on Multiagent Cooperation With Deep Reinforcement Learning.

Among various value decomposition-based multiagent reinforcement learning (MARL) algorithms, the overall performance of the multiagent system is represented by a scalar global Q value and optimized by minimizing the temporal difference (TD) error with respect to that global Q value. However, the global Q value cannot accurately model the distributed dynamics of the multiagent system, since it is only a simplified representation for different individual Q values of agents. To explicitly consider the correlations between different cooperative agents, in this article, we propose a distributional framework and construct a practical model called distributional multiagent cooperation (DMAC) from a novel distributional perspective. Specifically, in DMAC, we view the individual Q value for the executed action of a random agent as a value distribution, whose expectation can further represent the overall performance. Then, we employ distributional RL to minimize the difference between the estimated distribution and its target for the optimization. The advantage of DMAC is that the distributed dynamics of agents can be explicitly modeled, and this results in better performance. To verify the effectiveness of DMAC, we conduct extensive experiments under nine different scenarios of the StarCraft Multiagent Challenge (SMAC). Experimental results show that the DMAC can significantly outperform the baselines with respect to the average median test win rate.