{rfName}
As

Indexed in

Citations

1

Altmetrics

Analysis of institutional authors

Arriaga, CarlosCorresponding AuthorPozo, AlejandroAuthorConde, JavierAuthorAlonso, AlvaroAuthor

Share

March 4, 2026
Publications
>
Article
No

Assessing Latency in ASR Systems: A Methodological Perspective for Real-Time Use

Publicated to: IEEE INTERNET COMPUTING. 29 (5): 17-24 - 2025-09-01 29(5), DOI: 10.1109/mic.2025.3614363

Authors:

Arriaga, Carlos; Pozo, Alejandro; Conde, Javier; Alonso, Alvaro
[+]

Affiliations

Univ Politecn Madrid, Madrid 28040, Spain - Author

Abstract

Automatic speech recognition (ASR) systems generate real-time transcriptions but often miss nuances that human interpreters capture. While ASR is useful in many contexts, interpreters-who already use ASR tools such as Dragon-add critical value, especially in sensitive settings such as diplomatic meetings where subtle language is key. Human interpreters not only perceive these nuances but can adjust in real time, improving accuracy, while ASR handles basic transcription tasks. However, ASR systems introduce a delay that does not align with real-time interpretation needs. The user-perceived latency of ASR systems differs from that of interpretation because it measures the time between speech and transcription delivery. To address this, we propose a new approach to measuring delay in ASR systems and validate if they are usable in live interpretation scenarios.
[+]

Keywords

Artificial intelligenceDelaysHardwareLoss measurementMathematical modelsMeasurementReal-time systemsSpeech to textTime measurementTransformers

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal IEEE INTERNET COMPUTING due to its progression and the good impact it has achieved in recent years, according to the agency WoS (JCR), it has become a reference in its field. In the year of publication of the work, 2025, it was in position 19/129, thus managing to position itself as a Q1 (Primer Cuartil), in the category Computer Science, Software Engineering.

[+]

Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2026-04-09:

  • The use, from an academic perspective evidenced by the Altmetric agency indicator referring to aggregations made by the personal bibliographic manager Mendeley, gives us a total of: 10.
  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 10 (PlumX).

With a more dissemination-oriented intent and targeting more general audiences, we can observe other more global scores such as:

  • The Total Score from Altmetric: 1.
  • The number of mentions on the social network X (formerly Twitter): 1 (Altmetric).

It is essential to present evidence supporting full alignment with institutional principles and guidelines on Open Science and the Conservation and Dissemination of Intellectual Heritage. A clear example of this is:

  • Assignment of a Handle/URN as an identifier within the deposit in the Institutional Repository: https://oa.upm.es/91436/

As a result of the publication of the work in the institutional repository, statistical usage data has been obtained that reflects its impact. In terms of dissemination, we can state that, as of

  • Views: 64
  • Downloads: 191
[+]

Leadership analysis of institutional authors

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (ARRIAGA PRIETO, CARLOS) and Last Author (ALONSO GONZALEZ, ALVARO).

the author responsible for correspondence tasks has been ARRIAGA PRIETO, CARLOS.

[+]

Project objectives

Este trabajo persigue los siguientes objetivos: analizar la latencia en sistemas de reconocimiento automático de voz (ASR) desde una perspectiva metodológica; evaluar la diferencia entre la latencia percibida por el usuario (UPL) y la latencia en interpretación humana en tiempo real; determinar la adecuación de los sistemas ASR para su uso en escenarios de interpretación en vivo; caracterizar el impacto de la demora en la precisión y utilidad de las transcripciones generadas por ASR; y validar un nuevo método para medir el retraso en sistemas ASR, con especial atención a contextos sensibles como reuniones diplomáticas donde las sutilezas del lenguaje son cruciales.
[+]

Most relevant results

El estudio aborda la evaluación de la latencia en sistemas de reconocimiento automático de voz (ASR) para su uso en tiempo real. Los resultados más relevantes son: 1) Los sistemas ASR generan transcripciones en tiempo real pero presentan una latencia que no cumple con los requisitos de interpretación simultánea. 2) La latencia percibida por el usuario (UPL) en ASR difiere significativamente de la latencia en interpretación humana, afectando la sincronización. 3) Se propone un nuevo método para medir la demora en sistemas ASR, que permite evaluar su idoneidad en escenarios de interpretación en vivo. 4) La validación del método confirma que, aunque ASR es útil para tareas básicas, no reemplaza la capacidad de ajuste en tiempo real de intérpretes humanos.
[+]

Awards linked to the item

The authors would like to acknowledge the support of the FUN4DATE (PID2022-136684OB-C22) project funded by the Spanish Agencia Estatal de Investigacion (AEI 10.13039/501100011033), the TUCAN6-CM (TEC-2024/COM-460) project funded by CM (ORDEN5696/2024), and the Ministerio de Ciencia, Innovacion y Universidades (Grant FPU21/03069).
[+]