Resumo-A demanda por alta qualidade de experiência em sistemas de comunicação tem aumentado com a utilização de sistemas de teleconferência, o que, por sua vez, estimulou a procura por sistemas confiáveis de avaliação de qualidade. Ferramentas para monitoração durante a operação do sistema, em particular, permitem que os sinais sendo transmitidos tenham a sua qualidade avaliada e as degradações que o estão atingindo identificadas sem interrupção do serviço. Neste artigo, são apresentados dois cenários para monitoração de qualidade de sistemas de teleconferência, cada um contendo dois pontos de medição onde podem ser posicionadas ferramentas de monitoração nãointrusiva (INMDs). São levantados os tipos de degradação que podem ser monitorados em cada ponto de medição, além de critérios para o projeto dos respectivos INMDs. Os modelos propostos podem servir de guia para a geração de sinais degradados adequados para testes subjetivos. Palavras-Chave-teleconferência, degradações acústicas, avaliação não-intrusiva de qualidade, INMDAbstract-Teleconference systems have increased the demand for high quality of experience in speech communication, which, in turn, calls for reliable quality assessment tools. In-service monitoring tools, in particular, aim to assess the quality of the transmitted signal as well as to identify impairments that might occur during the operation of the system. This paper presents two scenarios for quality monitoring of teleconference systems, each of them containing two measurement points where in-service non-intrusive measurement devices (INMDs) can be located. The impairment types that can be monitored at each measurement point are elicited, as well as design constraints on their respective INMDs. The proposed models can also guide the generation of impaired signals to be employed in subjective listening tests.
Modern teleconference systems have set a new paradigm for speech quality, calling for a more rigorous control over potential impairments and resulting quality of service. Reliable and efficient tools for quality assessment (QA) of speech should be automatic and capable of emulating subjective tests. The present paper addresses this topic by proposing a simple teleconference model (called TMAI) intended as a framework to the design of QA tests for acoustically impaired speech. A procedure for building a database of reference and degraded signals to be employed in QA tests which uses the TMAI is described.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.