The Interspeech 2026 review form, explained

How Interspeech reviewers read your paper

Interspeech reviews (double-blind, CMT) rate appropriateness, novelty, technical correctness, clarity, reproducibility and references, give an overall recommendation and write detailed comments (overall impression, novelty, clarity, what to improve) that justify the scores. Long papers are judged on depth of contribution, originality, technical correctness, clarity, quality of references and potential long-term impact. Meta-reviewers consolidate the reviews.

• Detailed comments must justify every score (at least ~120 words).
• Do not penalize non-native English as long as the content is clear.
• Constructive and specific; name missing references.

Where the bar sits. Interspeech accepts roughly 50% of regular papers (official special-sessions call); the new long-paper track targets below 30%. On this 1–6 scale a mean of ≥ 3.75 (Weak Accept or better) is a rough proxy for acceptance.

The reviewer form, field by field

In the order reviewers see it, with every score and its official wording.

1. 01

   Appropriateness Of Topic For The Conference

   Score · 1–4

   Fit to speech science and technology. Explain a 1 or 2 in the comments.

   1. 4Very appropriate
   2. 3Appropriate
   3. 2Marginally appropriate
   4. 1Not appropriate
2. 02

   Novelty And Originality

   Score · 1–4

   Originality relative to prior speech/audio work; cite the prior work for low scores.

   Score	Meaning
   4	Very novel and/or innovative
   3	Novel
   2	Somewhat incremental
   1	Not novel

3. 03

   Technical Correctness

   Score · 1–4

   Soundness of methods, experiments and statistics.

   Score	Meaning
   4	Technically sound
   3	Mostly sound, minor issues
   2	Some significant issues
   1	Major technical flaws

4. 04

   Clarity Of Presentation

   Score · 1–4

   The English need not be flawless; judge whether the content is understandable.

   Score	Meaning
   4	Very clear
   3	Clear enough, could benefit from some revision
   2	Difficult to follow in places
   1	Unclear

5. 05

   Reproducibility

   Score · 1–4

   Data, setup, hyperparameters and code availability.

   1. 4Easily reproducible
   2. 3Mostly reproducible
   3. 2Hard to reproduce
   4. 1Not reproducible
6. 06

   Quality Of References

   Score · 1–4

   References should be peer-reviewed where possible; name missing work.

   Score	Meaning
   4	Excellent
   3	Adequate
   2	Some important references missing
   1	Inadequate

7. 07

   Overall Recommendation

   Score · 1–6

   Overall recommendation, consistent with the sub-scores.

   Score	Meaning
   6	Definite Accept I feel strongly that this paper must be accepted
   5	Accept
   4	Weak Accept
   3	Weak Reject
   2	Reject
   1	Definite Reject

8. 08

   Strengths

   List of points

   Part of “Detailed Comments For Authors” on the official form.

   Overall impression, novelty/originality and innovation, with specifics.

9. 09

   Weaknesses And Suggested Improvements

   List of points

   Part of “Detailed Comments For Authors” on the official form.

   What to improve, with specifics. Together with the strengths, at least 120 words, justifying the scores.

10. 10

    Reviewer Confidence

    Score · 1–4

    Selecting a value confirms you are competent to review the paper.

    Score	Meaning
    4	Very Confident - I consider myself an expert in this area
    3	Confident - I am familiar with this area
    2	Somewhat confident - I have some familiarity with this area
    1	Not confident - this area is outside my expertise

Area chair meta-review

Interspeech meta-reviewers consolidate reviews for the TPC; the form is not public.

• Accept
• Reject

Interspeech author checklist

Reviewers check these. Gaps are easy points to lose.

1. ISCA Code of Ethics, pre-prints policy and conference policy read
2. At most 6 pages (regular) or 10 (long paper); last pages only for acknowledgements, AI disclosure and references
3. Fully anonymized, including PDF metadata, self-citations and supplementary repositories
4. Generative AI used only for editing and polishing, reported in the dedicated section
5. Scientific reporting checklist answered in the submission form

Policy on LLMs in reviewing