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
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%PacificAI/langtest →
- PossiblePossibly related (embedding) · 50%thu-pacman/chitu →
- PossiblePossibly related (embedding) · 46%EuroEval/EuroEval →
- PossiblePossibly related (embedding) · 46%epam/ai-dial-core →
- FuzzySimilar title/name (fuzzy) · 84%huggingface/speech-to-speech →
“Fuzzy title match (0.92): “SPEARBench: A Benchmark for Naturalness Evaluation in Stream” ≈ “huggingface/speech-to-speech””
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzySimilar title/name (fuzzy) · 59%jeinlee1991/chinese-llm-benchmark →
“Fuzzy title match (0.73): “SPEARBench: A Benchmark for Naturalness Evaluation in Stream” ≈ “jeinlee1991/chinese-llm-benchmark””