Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when targeting INTERSPEECH (INTERSPEECH) or deciding whether a computer-science manuscript fits this venue. Encodes conference fit, framing, evidence bar, submission-cycle checks, rebuttal posture, and desk-reject risks for speech processing.
Use when designing or auditing the experimental evidence for an INTERSPEECH paper — task-correct metrics (WER/CER, MOS/CMOS, EER/minDCF, PESQ/STOI), baselines reviewers accept, significance testing over utterances and seeds, condition coverage across speakers/noise/languages, and data hygiene for speech corpora.
Use when positioning an INTERSPEECH paper in the literature — tracing lineage through the ISCA Archive and its DOIs, covering the ICASSP/ASRU/SLT sibling circuit and challenge series, handling the speech-versus-NLP crossover canon, citing corpora properly, and avoiding the venue misattributions speech reviewers notice instantly.
Use when reasoning about how INTERSPEECH review actually works — area-based assignment inside ISCA's scientific program, multi-reviewer scoring and meta-review on CMT, what the rebuttal can and cannot move, oral/poster allocation, ISCA best student paper selection, and reading a decision letter for next-cycle strategy.
Use when deciding whether a project belongs at INTERSPEECH, the ISCA flagship speech conference, or should be routed to ICASSP, ASRU/SLT, Odyssey, SSW, ACL/EMNLP, or a speech journal — testing whether spoken language is the contribution, matching subfields to the reviewer pool, and choosing between the 4-page and Long Paper tracks.
Use when defending the research design of an International Organization (IO) manuscript on international-level questions — causal identification with dyadic/TSCS/network data, case selection and process tracing for international cases, survey/conjoint experiments on foreign-policy attitudes, or formal-empirical linkage. IO judges each IR tradition on its own terms and verifies results and proofs before final acceptance. Strengthens the design; it does not write code.
Use when designing or auditing IPSN-lineage evaluations, covering real testbeds and deployments, ground-truth instrumentation, energy/latency/footprint measurement on real hardware, on-device/TinyML profiling, estimation-theoretic baselines and bounds, and matching evidence to the shape of each sensing claim across the IP and SPOTS tracks.
Use when reasoning about how an IPSN-lineage submission is evaluated, covering double-blind review, the per-track (IP / SPOTS) program committees, the rebuttal, Best Paper and Best Research Artifact judging, and how IPSN's process differs from SenSys's revision model, OpenReview venues, and CPS-IoT Week neighbors.
Use when designing or auditing IROS experiments — real-robot trial counts, success criteria set in advance, reset procedures, failure taxonomies, baseline fairness on matched hardware, sim-to-real gap reporting, small-n statistics, and the claim-to-evidence ladder that embodied-systems reviewers apply before they trust a demo.
Use when reasoning about IROS peer review — the PaperPlaza Associate-Editor/Editor pipeline, the traditional no-rebuttal single-notification model, how the video and embodied evidence steer reviewers, the 2026 double-anonymous posture, decision criteria for systems papers, and IEEE Xplore proceedings outcomes.