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

2024/09/09 by Carlos Arriaga, Arriaga, Carlos, Alejandro del Pozo +5
Biochemistry, Genetics and Molecular Biology · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Gene expression and cancer classification #I.2.7 #Molecular Biology Techniques and Applications #RNA and protein synthesis mechanisms #Sound (cs.SD)

paper · pdf · doi:10.48550/arxiv.2409.05674

openalex publication_date 2024/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Low Latency ASR for Simultaneous Speech Translation
• Defining maximum acceptable latency of AI-enhanced CAI tools
• Universal ASR: Unifying Streaming and Non-Streaming ASR Using a Single Encoder-Decoder Model
• A Survey on Non-Intrusive ASR Refinement: From Output-Level Correction to Full-Model Distillation
• An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications