SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech. However, standard speech and text benchmarks do not capture whether these systems behave naturally in conversations, where timing, turn-taking, prosody, interpersonal stance, language and dialect consistency, and relationship-aware appropriateness jointly shape perceived quality. We introduce SPEARBench, a benchmark for evaluating naturalness in speech-to-speech language models from question-answer interactions. SPEARBench constructs controlled dialogue prompts from the Seamless Interaction
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorThomas Thebaud →
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
- Linked via arxiv authorYuzhe Wang →
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
- Linked via arxiv authorYuhao Zhang →
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
- Linked via arxiv authorSathvik Manikantan Napa Ugandhar →
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
- Linked via arxiv authorAshish Hallur →
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
- Linked via arxiv authorGeorgi Tinchev →
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
- Linked via arxiv authorVenkatesh Ravichandran →
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
- Linked via arxiv authorLaureano Moro-Velazquez →
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models