Pith.

Audio and Speech Processing · arXiv:2611.16787 v1 · submitted 12 Nov 2026 · 12 references

MESH: Multi-receiver Evaluation of Spatial Hearing across Egocentric and Allocentric Views

Wen Wen, Bohan Li, KwanHo Tam, Yu Xi, Jing Peng, Shuai Wang, Kai Yu

The paper says

“Spatial hearing in multi-receiver environments requires identifying who speaks, where they are, and how they move.”

more of the abstract

Existing benchmarks evaluate spatial prediction, transcription, tracking, and distributed speech processing, but offer limited evaluation of whether speech signal remains associated with the correct physical source across receivers and motion. We introduce MESH, which evaluates this association through egocentric and allocentric views of shared acoustic scenes. The egocentric view uses local recordings and peer metadata, while the allocentric view combines synchronized recordings from multiple receivers in a shared 3D world frame. MESH contains nearly 40,000 questions across 13 static and dynamic localization and spatial transcription tasks. We evaluate eleven audio-model configurations and a language-model agent using specialist tools. The best static distance-estimation and dynamic direction-tracking accuracies are only 21.90% and 41.54%, respectively, while the lowest word error rates across four transcription tasks range from 59.15% to 73.10%. Ablation studies and additional experiments reveal that existing models are not yet able to effectively leverage peer information and struggle to handle multi-speaker and dynamic scenarios. These findings highlight the gap between access to distributed acoustic information and its effective use for spatial speech understanding. We release the dataset and evaluation code to support further research on collaborative and distributed spatial hearing.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: major revision.

A thorough, well-constructed benchmark for multi-receiver spatial speech understanding; the simulation-to-reality gap is real but the paper acknowledges it, and the benchmark is still valuable for controlled comparisons. This line is wrong

4 major objections · 10 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 12 references say.

The paper says, at Limitations (Observation assumptions)

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.86):

“Generalization to spontaneous conver- sations, other languages, and physical recording environments remains untested.”

Pith says: Objection 1 of 4 · major

The central claim that current models cannot effectively use distributed acoustic information rests entirely on simulated scenes with ideal assumptions (synchronized recordings, known poses, ideal self-playback removal, horizontal motion, fixed height). The authors acknowledge this limitation (lines [b186], [b191]), but the claim is about a fundamental capability gap, not just simulation performance.

more of objection 1

Real-world factors (clock drift, calibration errors, missing recordings, asynchronous streams, non-ideal self-playback removal, 3D motion, varying microphone types) could substantially change difficulty or relative model rankings. The paper provides no evidence—even a small-scale real-world recording or perturbation analysis—that the simulation findings are robust to these factors. This is a load-bearing concern because the benchmark's validity for real-world deployment depends on it. The authors should either temper the claim to be about simulated environments or provide evidence of robustness.

The paper says, at §4.3 / Appendix B.3 (Controlled information comparisons)

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.78):

“Shorter prompts are a confound; no length-matched placebo is included.”

Pith says: Objection 2 of 4 · major

The ablation study on peer information and distributed recordings is conducted on a subset (100 rooms, 5,090 questions) and uses only three models. The authors acknowledge that removing metadata also changes prompt length, which is a confound (line [b385]). The results show inconsistent effects, and the sample size may be insufficient to draw strong conclusions.

more of objection 2

The claim that 'peer information provides limited benefits' and 'distributed recordings offer selective gains' is supported by the data, but the analysis is not comprehensive enough to rule out that better integration methods could yield consistent improvements. The authors should discuss this limitation more explicitly.

The paper says, at §4.2 / Table 2 (Egocentric results)

The review did not quote this passage.

Pith says: Objection 3 of 4 · major

The Overall score (Eq. 4) weights localization and transcription equally within each view, but the composition of tasks differs between views (8 egocentric vs. 5 allocentric). The score is also sensitive to the threshold choice (20° direction error, 20% distance error, 2 m position error).

more of objection 3

While the authors report task-level metrics separately, the Overall score is used for summary comparisons. The authors should clarify whether the Overall score is intended as a primary metric or just an illustrative aggregate, and discuss its limitations.

The paper says, at §3.4 / Appendix C.2 (Data curation pipeline)

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.95):

“The preliminary listening audit covers only a small subset of scenes and does not establish cross-receiver consistency.”

Pith says: Objection 4 of 4 · major

The manual validation covers only 57 scene-question reviews (36 pilot, 21 formal) out of ~40,000 questions, with no inter-rater agreement established (lines [b190], [b210]). The authors acknowledge this limitation. However, the benchmark is presented as a reliable evaluation tool. The limited validation scope means that undetected annotation errors could affect results. The authors should either expand validation or explicitly state that the benchmark is preliminary and may contain errors.

10 minor objections

The paper says, at Abstract

Pith says: minor objection 1 of 10

The abstract states 'nearly 40,000 questions' but the main text says 'approximately 40,000 questions' (line [b33]). This is consistent, but the exact count should be specified for reproducibility.

The paper says, at §1 (Introduction)

Pith says: minor objection 2 of 10

The introduction mentions 'an exhibition hall' as a concrete example, but the benchmark uses simulated exhibition rooms. This could be clarified to avoid implying real-world validation.

show 8 more

The paper says, at §3.1 (Scene and Coordinate Views)

Pith says: minor objection 3 of 10

The definition of egocentric view uses Eq. (1) for relative position, but the paper does not specify how orientation is handled for direction queries (azimuth/elevation). This is clear from context but could be explicitly stated.

The paper says, at Table 2 and Table 3

Pith says: minor objection 4 of 10

The tables use abbreviations like 'Acc↑' and 'RelAcc↑' without defining them in the caption. They are defined in §4.1, but a brief reminder in the caption would improve readability.

The paper says, at §4.1 (Evaluation metrics)

Pith says: minor objection 5 of 10

The threshold for direction error is 20°, for distance error 20% relative, and for position error 2 m. These thresholds are reasonable but arbitrary. The authors should discuss sensitivity to threshold choice or provide additional metrics (e.g., mean absolute error).

The paper says, at Appendix B.1 (Metrics and Reporting Scope)

Pith says: minor objection 6 of 10

The definition of coverage and handling of missing predictions is clear, but the diagnostic error assignment (180° for missing directions) could be mentioned in the main text for transparency.

The paper says, at Figure 2

Pith says: minor objection 7 of 10

The figure shows WER vs. human sources, SNR, and SIR. The connecting lines between conditions are described as 'ordered conditions, not a continuous numerical interval to Clean' (line [b363]). This is a minor clarity issue; the authors could use bar charts instead of line plots to avoid implying interpolation.

The paper says, at Appendix C.4 (Human Review Interface and Procedure)

Pith says: minor objection 8 of 10

The listening audit is described in detail, but the sample size (57 reviews) is very small. The authors acknowledge this, but the inclusion of this audit in the main paper (via reference) might give a false impression of thorough validation. Consider moving to supplementary material or clearly stating its preliminary nature.

The paper says, at References

Pith says: minor objection 9 of 10

Some references are to arXiv preprints (e.g., [Biswas et al., 2026], [Hu et al., 2026], [Kumar et al., 2026]). This is acceptable for a rapidly evolving field, but the authors should ensure that cited results are stable and not subject to major revision.

The paper says, at General

Pith says: minor objection 10 of 10

The paper is generally well-written and the benchmark design is thorough. The code and dataset release is commendable and supports reproducibility.

What would settle it

Record a small set of real multi-receiver scenes (e.g., 10 rooms, 2-3 receivers, 1-2 moving speakers) with known ground truth (e.g., via motion capture and close-talk mics). Evaluate the best-performing model(s) from the paper (e.g., Qwen3.8-Omni-Flash, MESH-agent) on these real recordings using the same task definitions. If performance drops significantly (e.g., >20% relative degradation in accuracy or WER increase >10% absolute) compared to simulation, the simulation-to-reality gap is a critical concern. If performance is comparable, the concern is mitigated.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 13 Nov 2026

  1. Reader holds up confidence high
  2. Skeptic agrees: says it holds up only with conditions 7 s · 23,858 tokens read, 617 written Simulated scenes lack ecological validity for the claim that current models cannot effectively use distributed acoustic information; the simulation-to-reality gap is unaddressed.
  3. Editor wrote the verdict above 5 s · 24,652 tokens read, 572 written
  4. Referee major revision: 4 major objections, 10 minor 12 s · 24,230 tokens read, 1,645 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

This is a solid benchmark paper. The core contribution is MESH, a dataset and evaluation protocol that combines multi-receiver FOA recordings, receiver motion, numerical trajectories, and spatially cued transcription with physical error metrics. No existing benchmark does all of that together. The egocentric/allocentric view distinction is a useful conceptual framing, and the 13 tasks cover a sensible range of static and dynamic localization and transcription problems. The construction pipeline is well-documented, with automated checks and manual validation. The authors evaluate eleven model configurations and an agentic system, and the results are informative: current models perform poorly on associating speech with the correct physical source, especially in crowded and dynamic scenes. The paper is honest about its limitations—simulated data, English only, horizontal motion, ideal assumptions—and the dataset and code are released.

The main soft spot is the simulation-to-reality gap. The central claim that current models cannot effectively use distributed acoustic information rests entirely on simulated scenes with synchronized recordings, known poses, ideal self-playback removal, and no clock drift or calibration errors. The authors acknowledge this, but they do not provide any evidence—not even a small-scale real-world recording or a perturbation analysis—that the findings are robust to real-world factors. This is a load-bearing concern if the benchmark is meant to guide real-world deployment. However, the paper is careful to frame the results as highlighting a gap in controlled conditions, and the benchmark is still valuable for comparing models under those conditions. The stress-test note overstates this concern: the paper does not claim real-world validity, and the limitations section is explicit. The benchmark is a useful tool for measuring progress in a controlled setting, not a deployment-ready evaluation.

Minor issues: the MESH-agent evaluation used a release with prior results rather than an untouched test set, and the contribution of agentic planning is not isolated. The confidence intervals do not account for multiple comparisons. These are acknowledged and are minor.

Who this is for: researchers working on spatial audio understanding, multi-receiver speech processing, or embodied listening. The paper deserves a serious referee. I would accept peer review.

Recommendation: Accept with minor revisions. The authors should add a small-scale real-world validation or at least a perturbation analysis to address the simulation-to-reality gap, but the paper is already a solid contribution as is.

The strongest objection

The central claim—that current models cannot effectively use distributed acoustic information for spatial speech understanding—rests entirely on simulated acoustic scenes (SoundSpaces 2.0 FOA rendering, horizontal motion, fixed height, ideal self-playback removal, synchronized recordings, known poses). The authors acknowledge this limitation (Limitations: 'Generalization to spontaneous conversations, other languages, and physical recording environments remains untested.'). However, the claim is not merely about simulation performance; it is about a fundamental gap in capability. If real-world conditions (clock drift, calibration errors, missing recordings, asynchronous streams, non-ideal self-playback removal, 3D motion, varying microphone types) substantially change the difficulty or the relative model rankings, then the conclusion that 'existing models are not yet able to effectively leverage peer information' may not hold in practice. The paper does not provide any evidence—even a small-scale real-world recording or a perturbation analysis—that the simulation findings are robust to these real-world factors. The weakest assumption is that the simulation is representative enough to support a general claim about model capability. This is a load-bearing concern because the entire benchmark's validity for real-world deployment depends on it.

The reader's weakest_assumption correctly identifies the simulation-to-reality transfer as the weakest point. The paper's central claim is about a fundamental limitation of current models, but the evidence is entirely from simulated data. The authors acknowledge this limitation, but the claim's strength depends on the assumption that simulation is representative. The concrete test I propose is feasible (small-scale real recording) and would directly address the concern. I recommend CONDITIONAL acceptance: the paper should be accepted if the authors either provide real-world validation or substantially weaken the claim to be about simulated environments only. The reader's verdict was ACCEPT with HIGH confidence; I think the confidence should be lower given this unresolved concern. The paper is otherwise strong, but the central claim's generality is not fully supported.

The referee's report

If the benchmark is valid, it provides a systematic evaluation of a relatively underexplored capability: associating speech with the correct physical source across receivers and motion. The benchmark design is thorough, with automated checks and manual validation. The results consistently show that current models struggle, which could guide future research. However, the significance is tempered by the simulation-to-reality gap and the acknowledged limitations.

Pith's reading of the paper (a machine's summary, not the authors')

The paper introduces MESH, a benchmark for evaluating spatial speech understanding in multi-receiver environments. It assesses whether AI systems can associate speech with the correct physical source across both egocentric (receiver-relative) and allocentric (world-frame) views. The authors test eleven audio-model configurations and a language-model agent on nearly 40,000 questions spanning static and dynamic localization and transcription tasks. The central finding is that current systems perform poorly: the best static distance estimation accuracy is only 21.90%, the best dynamic direction tracking is 41.54%, and word error rates for spatial transcription range from 59.15% to 73.10%. Ablation studies show that providing peer metadata and distributed recordings yields only selective and inconsistent improvements, underscoring a fundamental gap between access to distributed acoustic information and its effective use for spatial hearing.

What carries the argument. The benchmark itself is the key machinery: a controlled dataset of simulated exhibition-room acoustic scenes with up to three human speakers and three robot receivers, each recording synchronized first-order Ambisonic audio. The central design is the separation of egocentric and allocentric views, which allows testing whether models can associate acoustic observations with physical sources in both receiver-relative and world coordinates. The 13 task definitions (e.g., ES-CDir, AD-Trans) specify exactly what cues are provided (transcripts, spatial anchors, regions) and what must be predicted (direction, distance, position, transcript), enabling precise diagnosis of which aspects of spatial hearing fail.

Core claim. The paper establishes that existing audio-language models and agentic systems cannot reliably associate speech with the correct physical source in multi-receiver acoustic scenes, particularly when multiple speakers are present or when sources or receivers move. The benchmark systematically tests this association through 13 tasks that require either localizing a speaker identified by transcript or transcribing speech identified by spatial cues, in both static and dynamic settings. The results show that direction estimates can be moderately accurate (up to 50% for transcript-conditioned direction) but distance estimates remain poor (below 22%), and spatial transcription frequently recovers speech from the wrong person (25% of positive answers match another human's speech). The paper argues that this reveals a fundamental gap between having access to distributed acoustic information and being able to use it effectively.

The premise it rests on. The simulated acoustic scenes using SoundSpaces 2.0 with first-order Ambisonic rendering, horizontal motion, fixed height, and ideal self-playback removal are representative enough of real-world multi-receiver environments to support the general conclusion that current models cannot effectively use distributed acoustic information for spatial speech understanding.

If the paper is right (Pith's inferences, not the authors')

Future spatial audio models must explicitly solve the speech-source association problem rather than treating localization and transcription as separate tasks.

Peer information and distributed recordings, while conceptually useful, require new architectural mechanisms to be reliably exploited; current models show no consistent benefit from them.

The finding that distance estimation and dynamic tracking are far weaker than direction estimation suggests that models rely on interaural cues but fail to integrate intensity, reverberation, or motion cues.

The high rate of wrong-speaker transcription (25% of positive answers) indicates that spatial attention mechanisms in current audio-language models are not sufficiently selective.

The benchmark provides a standardized evaluation protocol that can drive progress in collaborative and distributed spatial hearing, analogous to how ImageNet drove visual recognition.

The failure to use peer metadata and distributed recordings suggests that current architectures lack a mechanism for cross-receiver feature alignment or geometric reasoning; this points toward a need for explicit 3D spatial representations rather than implicit learned embeddings.

The gap between direction and distance accuracy implies that models may be exploiting the strong directional cues available in first-order Ambisonics (which encode pressure gradients) but not the weaker distance cues (intensity, direct-to-reverberant ratio), suggesting that training on distance-related tasks or incorporating binaural cues could help.

The benchmark's simulated nature (horizontal motion, fixed height, ideal self-playback removal) means that real-world deployment would likely reveal even larger gaps, especially with unknown receiver poses, clock drift, and non-ideal microphone arrays.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Spatial hearing in multi-receiver environments requires identifying who speaks, where they are, and how they move. Existing benchmarks evaluate spatial prediction, transcription, tracking, and distributed speech processing, but offer limited evaluation of whether speech signal remains associated with the correct physical source across receivers and motion. We introduce MESH, which evaluates this association through egocentric and allocentric views of shared acoustic scenes. The egocentric view uses local recordings and peer metadata, while the allocentric view combines synchronized recordings from multiple receivers in a shared 3D world frame. MESH contains nearly 40,000 questions across 13 static and dynamic localization and spatial transcription tasks. We evaluate eleven audio-model configurations and a language-model agent using specialist tools. The best static distance-estimation and dynamic direction-tracking accuracies are only 21.90% and 41.54%, respectively, while the lowest word error rates across four transcription tasks range from 59.15% to 73.10%. Ablation studies and additional experiments reveal that existing models are not yet able to effectively leverage peer information and struggle to handle multi-speaker and dynamic scenarios. These findings highlight the gap between access to distributed acoustic information and its effective use for spatial speech understanding. We release the dataset and evaluation code to support further research on collaborative and distributed spatial hearing.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-11-13

The authors' main claim, as the classifier picked it out 0.91

“These findings highlight the gap between access to distributed acoustic information and its effective use for spatial speech understanding.”

How the main claim is stated: asserted 0.97

What the abstract itself states, as probabilities: claims first 0.14 · states limitation 0.39 · human participants 0.23 · controlled comparison 0.25 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.65 · mentions code or data availability 0.99

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Spatial hearing in multi-receiver environments requires identifying who speaks, where they are, and how they move. background 1.00 0.05 0.02 asserted 1.00
Existing benchmarks evaluate spatial prediction, transcription, tracking, and distributed speech processing, but offer limited evaluation of whether speech signal remains associated with the correct physical source across receivers and motion. gap 0.98 0.07 0.04 asserted 1.00
We introduce MESH, which evaluates this association through egocentric and allocentric views of shared acoustic scenes. contribution 1.00 0.90 0.05 asserted 1.00
The egocentric view uses local recordings and peer metadata, while the allocentric view combines synchronized recordings from multiple receivers in a shared 3D world frame. method 0.94 0.74 0.03 asserted 1.00
MESH contains nearly 40,000 questions across 13 static and dynamic localization and spatial transcription tasks. method 0.64 0.90 0.03 asserted 1.00
We evaluate eleven audio-model configurations and a language-model agent using specialist tools. method 0.91 0.94 0.03 asserted 0.99
The best static distance-estimation and dynamic direction-tracking accuracies are only 21.90% and 41.54%, respectively, while the lowest word error rates across four transcription tasks range from 59.15% to 73.10%. result 1.00 0.95 0.21 asserted 1.00
Ablation studies and additional experiments reveal that existing models are not yet able to effectively leverage peer information and struggle to handle multi-speaker and dynamic scenarios. result 0.69 0.94 0.39 asserted 1.00
These findings highlight the gap between access to distributed acoustic information and its effective use for spatial speech understanding. interpretation 1.00 0.77 0.69 asserted 0.97
We release the dataset and evaluation code to support further research on collaborative and distributed spatial hearing. contribution 0.69 0.88 0.05 asserted 0.94

What kind of paper the classifier reports this is: dataset or benchmark 1.00 · evidence from observation or experiment 0.99

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 7,540 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (8)
Figure 1 of the paper
Figure 1. Overview of MESH: (a) scene sources, (b) coordinate views and available information, (c) construction
Figure 2 of the paper
Figure 2. Egocentric transcription WER. Clean denotes
Figure 3 of the paper
Figure 3. Transcription outcome distribution over 12,925 positive questions per configuration. Mutually exclusive
Figure 4 of the paper
Figure 4. Selected paired information effects with 95% room-bootstrap intervals. Positive values favor keeping
Figure 5 of the paper
Figure 5. A frozen task query, after shared public con
Figure 6 of the paper
Figure 6. The listening-review interface. (a) Reviewers configure the sampling plan, navigate the review queue,
Figure 7 of the paper
Figure 7. Direction can be accurate while distance is
Figure 8 of the paper
Figure 8. The same two spatial queries across eleven direct configurations. Request boxes summarize the supplied

Figures are the authors', reproduced from the paper.

References (12)
  1. [3] MiDashengLM-Spatial: Unifying General Audio Understanding and Spatial Awareness.arXiv preprint arXiv:2610.11156. Sonal Kumar, Sinan Hersek, Artem Dementyev, Mengzhen Pan, Ishan Chatterjee, Anurag Kumar, Ramani Duraiswami, Dinesh Manocha, and Andrea Colaco on PithPith's reviewarXiv
  2. [4] SEA-LM: Egocentric spatial audio un- derstanding for wearable microphone arrays.arXiv preprint arXiv:2610.05610. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica on PithPith's reviewarXiv
  3. [5] Spatio-temporal audio language mod- eling for dynamic sound sources.arXiv preprint arXiv:2606.14141. Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur on PithPith's reviewarXiv
  4. [6] Qwen3-ASR Technical Report. arXiv preprint arXiv:2601.21337. Kazuki Shimada, Kengo Uchida, Yuichiro Koyama, Takashi Shibuya, Shusuke Takahashi, Yuki Mitsu- fuji, and Tatsuya Kawahara on PithPith's reviewarXiv
  5. [8] Audio-Mind: An Auditable Agentic 10 Framework for Audio Understanding.arXiv preprint arXiv:2605.28480. Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu, Xiong Wang, Jinzheng He, Yuxuan Wang, Xian Shi, Ting He, Xinfa Zhu, Yuanjun Lv, Yongqi Wang, Dake Guo, He Wang, Linhan Ma, Pei Zh... on PithPith's reviewarXiv
  6. [9] Qwen3-Omni Technical Report.arXiv preprint arXiv:2509.17765. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Day- iheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong... on PithPith's reviewarXiv
  7. [11] Spatial-Omni: Spatial audio under- standing integration in multimodal LLMs via FOA encoding.arXiv preprint arXiv:2606.10738. A Detailed Experimental Configurations Table 4 summarizes the evaluated interfaces. This appendix retains settings needed to interpret the comparisons; ... on PithPith's reviewarXiv
  8. [12] Its empty- answer accuracy is 22.50%. Qwen3.5-Omni-Plus components and uncer- tainty.The main tables report both interfaces’ Overall scores. Correct-empty accuracy is 6.00% (FOA-W) and 12.13% (FOA-sep). The FOA- sep-minus-FOA-W Overall differences have room- bootstrap interval... on Pith
  9. [2023] The CHiME-7 DASR Challenge: Distant Meeting Transcription with Multiple Devices in Diverse Sce- narios. InProc. CHiME 2023, pages 1–6. Christine Evers, Heinrich W. Löllmann, Heinrich Mellmann, Alexander Schmidt, Hendrik Barfuss, Patrick A. Naylor, and Walter Kellermann on Pith
  10. [2024] AIR-bench: Benchmarking large audio-language models via generative comprehension. InProceed- ings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa- pers), pages 1979–1998. Association for Computa- tional Linguistics. Zhisheng Zheng... on Pith
  11. [2025] AudioBench: A universal benchmark for audio large language models. InPro- ceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Compu- tational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4297–4316. Associ- at... on Pith
  12. [2026] RMS-AQA: A two-stage spatial audio question an- swering benchmark for real-world domestic environ- ments.arXiv preprint arXiv:2610.00935. Samuele Cornell, Matthew Wiesner, Shinji Watanabe, Desh Raj, Xuankai Chang, Paola Garcia, Matthew Maciejewski, Yoshiki Masuyama, Zhong-Qiu ... on PithPith's reviewarXiv

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment