PitchBench: Measuring Pitch Hearing in Audio-Language Models

• URL: http://arxiv.org/abs/2605.26176v1
• Date: Mon, 25 May 2026 05:37:15 GMT
• Title: PitchBench: Measuring Pitch Hearing in Audio-Language Models
• Abstract summary: We introduce PitchBench, an evaluation suite that measures pitch hearing in audio-language models (ALMs)<n>PitchBench comprises 28 experiments spanning absolute and relative pitch perception within sequences and chords, while varying loudness, note duration, sound source, time stretching, background noise, and other acoustic conditions.<n>We find that pitch hearing remains highly unreliable, with accuracy varying sharply by sound source, note duration, and notation format.
• Score: 9.085153261594623
• License: http://creativecommons.org/licenses/by/4.0/
• 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. This makes reliable musical perception a critical prerequisite: if a model cannot accurately hear the structure of sound, it cannot be trusted to reason about, teach, transcribe, or act on audio in the real world. Yet existing benchmarks rarely assess one of the most fundamental musical abilities underlying such perception: pitch hearing. Current evaluations tend to probe pitch hearing only indirectly, through higher-level tasks and often in multiple-choice formats, leaving open how reliably ALMs identify fine-grained pitch across instruments, acoustic conditions, and response formats. We introduce PitchBench, an evaluation suite that systematically measures pitch hearing in ALMs. PitchBench comprises 28 experiments spanning absolute and relative pitch perception within sequences and chords, while varying loudness, note duration, sound source, time stretching, background noise, and other acoustic conditions. Tasks range from identifying individual pitches in isolation to tracking a melodic line within a four-part musical texture. Evaluating frontier ALMs, we find that pitch hearing remains highly unreliable: models perform consistently poorly across settings, with accuracy varying sharply by sound source, note duration, and notation format. Current ALMs do not yet possess stable pitch perception, even for controlled synthetic and instrumental stimuli. Alongside the benchmark, we release PitchBench as a Python package containing the evaluation data and data generation tools to support future work on pitch-aware audio-language modeling.

Related papers

• TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models [58.80225070159013]
  Large audio-language models (LALMs) describe audio at the clip level but cannot assign timestamps to the events, speakers, or sounds they identify.<n>We present TEMPO, the first unified model to handle audio, speech, and music timestamping tasks.
  arXiv  Detail & Related papers  (2026-08-30T19:49:21Z)
• What Are You Listening to? Temporal Music Grounding for Audio-to-Text Large Language Models [4.715803044908279]
  We introduce temporal music grounding, a task in which a model returns one or more time spans corresponding to a queried musical note, event, or pattern.<n>We present MusicGroundingBench, a benchmark suite built by rendering algorithmically generated piano MIDI to audio.<n>Experiments show that temporal music grounding remains challenging for current audio-language models, whereas task-specific training yields substantial gains.
  arXiv  Detail & Related papers  (2026-08-30T00:17:28Z)
• FIGMA: Towards FIne-Grained Music retrievAl [65.98380295254817]
  Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.<n>We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens.<n>We propose FIGMA, a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment.
  arXiv  Detail & Related papers  (2026-06-04T18:05:39Z)
• Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models [56.91801348360746]
  Large audio-language models (LALMs) generalize across speech, sound, and music.<n> unified decoders can exhibit a emphtemporal smoothing bias<n>We propose emphTemporal Contrastive Decoding (TCD), a training-free decoding method for unified LALMs.
  arXiv  Detail & Related papers  (2026-04-16T02:30:41Z)
• HumMusQA: A Human-written Music Understanding QA Benchmark Dataset [2.7761207021407217]
  This paper introduces a meticulously structured approach to music evaluation, proposing a new dataset of 320 hand-written questions curated and validated by experts with musical training.<n>To demonstrate the use of the dataset, we benchmark six state-of-the-art LALMs and additionally test their robustness to uni-modal shortcuts.
  arXiv  Detail & Related papers  (2026-03-29T21:33:07Z)
• SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use Cases [27.340743922132067]
  SCENEBench targets a broad form of audio comprehension across four real-world categories: background sound understanding, noise localization, cross-linguistic speech understanding, and vocal characterizer recognition.<n>The purpose of this benchmark suite is to assess audio beyond just what words are said - rather, how they are said and the non-speech components of the audio.<n>We assess five state-of-the-art LALMs and find critical gaps: performance varies across tasks, with some tasks performing below random chance and others achieving high accuracy.
  arXiv  Detail & Related papers  (2026-03-10T16:15:12Z)
• AHELM: A Holistic Evaluation of Audio-Language Models [78.20477815156484]
  multimodal audio-language models (ALMs) take interleaved audio and text as input and output text.<n>AHELM is a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE and CoRe-Bench.<n>We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models.
  arXiv  Detail & Related papers  (2025-08-29T07:40:39Z)
• WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations [67.6147632074449]
  We introduce the World-of-Whale benchmark (WoW-Bench) to evaluate low-level auditory perception and cognition using marine mammal vocalizations.<n>WoW-Bench is composed of a Perception benchmark for categorizing novel sounds and a Cognition benchmark, inspired by Bloom's taxonomy, to assess the abilities to remember, understand, apply, and analyze sound events.<n>Experiments with state-of-the-art LALMs show performance far below human levels, indicating a need for stronger auditory grounding in LALMs.
  arXiv  Detail & Related papers  (2025-08-28T16:29:46Z)
• ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing [47.14083940177122]
  ThinkSound is a novel framework that enables stepwise, interactive audio generation and editing for videos.<n>Our approach decomposes the process into three complementary stages: semantically coherent, interactive object-centric refinement, and targeted editing.<n> Experiments demonstrate that ThinkSound achieves state-of-the-art performance in video-to-audio generation across both audio metrics and CoT metrics.
  arXiv  Detail & Related papers  (2025-06-26T16:32:06Z)
• CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following [12.638115555721257]
  CMI-Bench is a comprehensive music instruction following benchmark designed to evaluate audio-text LLMs on a diverse set of music information retrieval (MIR) tasks.<n>Unlike previous benchmarks, CMI-Bench adopts standardized evaluation metrics consistent with previous state-of-the-art MIR models.<n>We provide an evaluation toolkit supporting all open-source audio-textual LLMs, including LTU, Qwen-audio, SALMONN, MusiLingo, etc.
  arXiv  Detail & Related papers  (2025-06-14T00:18:44Z)
• Evaluation of pretrained language models on music understanding [0.0]
  We demonstrate that Large Language Models (LLM) suffer from 1) prompt sensitivity, 2) inability to model negation, and 3) sensitivity towards the presence of specific words. We quantified these properties as a triplet-based accuracy, evaluating the ability to model the relative similarity of labels in a hierarchical ontology. Despite the relatively high accuracy reported, inconsistencies are evident in all six models, suggesting that off-the-shelf LLMs need adaptation to music before use.
  arXiv  Detail & Related papers  (2024-09-17T14:44:49Z)
• RMSSinger: Realistic-Music-Score based Singing Voice Synthesis [56.51475521778443]
  RMS-SVS aims to generate high-quality singing voices given realistic music scores with different note types. We propose RMSSinger, the first RMS-SVS method, which takes realistic music scores as input. In RMSSinger, we introduce word-level modeling to avoid the time-consuming phoneme duration annotation and the complicated phoneme-level mel-note alignment.
  arXiv  Detail & Related papers  (2023-05-18T03:57:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.