PitchBench: Measuring Pitch Hearing in Audio-Language Models
The article introduces PitchBench, a new evaluation suite designed to measure pitch hearing in audio-language models (ALMs). It highlights the importance of reliable musical perception for ALMs in various applications, such as music tutoring and transcription. The findings indicate that current ALMs struggle with stable pitch perception across different conditions.
- ▪PitchBench comprises 28 experiments that assess absolute and relative pitch perception under varying acoustic conditions.
- ▪Current evaluations of ALMs often fail to directly measure pitch hearing, relying instead on higher-level tasks.
- ▪The study reveals that ALMs perform poorly in pitch perception tasks, with accuracy varying significantly based on sound source and note duration.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.26176 |
| Publication time | Wed, 27 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-27T04:07:56.398Z |
| Last seen | 2026-05-27T04:07:56.398Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | oxBIKbdfhwJ9 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Sound arXiv:2605.26176 (cs) [Submitted on 25 May 2026] Title:PitchBench: Measuring Pitch Hearing in Audio-Language Models Authors:Milan Liessens Dujardin, Song-Ze Yu, Craver Corbyn Thomas-Smith, David M. Chan, Karina Nguyen View a PDF of the paper titled PitchBench: Measuring Pitch Hearing in Audio-Language Models, by Milan Liessens Dujardin and 4 other authors View PDF HTML (experimental) Abstract:Audio-language models (ALMs) are increasingly used in real-world applications that require understanding music, from music tutoring and transcription to captioning, recommendation systems, and music production. More broadly, they are becoming an important component of multimodal AI systems that must reason from sensory input rather than text alone.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
