Search papers, labs, and topics across Lattice.
This paper introduces OpenSTBench, a comprehensive evaluation framework designed to assess speech translation systems across multiple dimensions, including translation quality, speech quality, and temporal consistency. By unifying the evaluation of speech-to-text and speech-to-speech translation in both offline and streaming contexts, the framework facilitates a more holistic comparison of heterogeneous systems. Experimental results reveal significant discrepancies in speech and temporal quality among systems that otherwise perform well in translation quality, highlighting the need for a multidimensional evaluation approach.
Strong translation quality doesn't guarantee high speech or temporal fidelity, revealing critical gaps in existing evaluation practices for speech translation systems.
Speech translation systems increasingly span speech-to-text translation (S2TT), speech-to-speech translation (S2ST), offline translation, and streaming generation, producing outputs that differ in modality, speech realization, and timing behavior. Existing evaluation practices assess important aspects such as translation quality, speech quality, and temporal quality, but these aspects are often evaluated under separate protocols, making it difficult to compare heterogeneous systems comprehensively. To address this gap, we present OpenSTBench, a unified multidimensional evaluation framework that organizes heterogeneous speech translation outputs into a shared evaluation format. OpenSTBench supports both S2TT and S2ST systems in offline and streaming settings, and jointly evaluates translation quality, speech quality, speaker preservation, emotion and paralinguistic fidelity, temporal consistency, and latency. Through experiments on representative speech translation systems, we show that systems with strong translation quality can still differ substantially in speech quality, as well as in temporal quality. OpenSTBench provides a reproducible protocol for analyzing these cross-dimensional differences and supporting application-oriented comparison of speech translation systems. The code and datasets are available at https://github.com/sjtuayj/OpenSTBench.
