arXiv subjects

Iran R. Roman

Publications and source records attributed to Iran R. Roman.

14 recordsLinked to original sources

arXiv2026

Mind the Microphone Gap: Benchmarking Array Upsampling Strategies for Latent Acoustic Mapping

Latent Acoustic Mapping (LAM) is a self-supervised learning method that generates high-resolution spherical acoustic maps from multichannel recordings without labelled data, matching supervised baselines on direction-of-arrival benchmarks. However, LAM degrades significantly with sparse 4-channel arrays, as the low-resolution cross-spectral matrix captures far less spatial information than the 32-channel inputs LAM was designed for. We benchmark a diverse set of upsampling architectures, spanning lightweight convolutional networks, iterative back-projection models, physics-informed networks, and generative adversarial approaches. We also study whether aligning these upsamplers with LAM by training them jointly or in different stages helps preserve the spatial structure that LAM depends on. Results show that the original full-resolution LAM is the strongest, that separately trained lightweight models are the most competitive learned approaches, and that representation alignment between the upsampler and LAM matters more than model complexity.

cs.SD↗

arXiv2026

Clean2FX: Label-conditioned modeling for clean-to-effect guitar audio transformations

We present Clean2FX, a study and demo of label-conditioned clean-to-effect transformation for electric guitar audio. Given a clean guitar input and a target effect label, the task is to synthesize the corresponding effected signal while preserving the musical content. Training and evaluation pairs are constructed from EGFxSet real, single tone recordings by assembling matched clean/effected chords, melodies, and mixed timelines. This allows for controlled comparison across effects. We evaluate four neural approaches under a common spectrogram-based transformation setting: two variational autoencoders and two U-Net models that differ in whether they operate on linear or log-magnitude representations. Performance is measured using linear-magnitude spectrogram MSE and Fr\'echet Audio Distance. The U-Net models outperform the variational autoencoder variants. Per-effect results show that distortion effects are most readily improved, whereas delay and reverb effects exhibit weaker FAD gains despite substantial spectral-error reductions. A conditioning-sensitivity diagnostic provides evidence that the best model responds to target labels rather than collapsing to a single transformation. Our demo website compares two models applied on real-world guitar performances outside training and validation data, providing audio and spectrogram examples of the practical clean-to-effect behavior.

cs.SD↗

arXiv2025

Evaluating Multimodal Large Language Models on Core Music Perception Tasks

Multimodal Large Language Models (LLMs) claim "musical understanding" via evaluations that conflate listening with score reading. We benchmark three SOTA LLMs (Gemini 2.5 Pro, Gemini 2.5 Flash, and Qwen2.5-Omni) across three core music skills: Syncopation Scoring, Transposition Detection, and Chord Quality Identification. Moreover, we separate three sources of variability: (i) perceptual limitations (audio vs. MIDI inputs), (ii) exposure to examples (zero- vs. few-shot manipulations), and (iii) reasoning strategies (Standalone, CoT, LogicLM). For the latter we adapt LogicLM, a framework combining LLMs with symbolic solvers to perform structured reasoning, to music. Results reveal a clear perceptual gap: models perform near ceiling on MIDI but show accuracy drops on audio. Reasoning and few-shot prompting offer minimal gains. This is expected for MIDI, where performance reaches saturation, but more surprising for audio, where LogicLM, despite near-perfect MIDI accuracy, remains notably brittle. Among models, Gemini Pro achieves the highest performance across most conditions. Overall, current systems reason well over symbols (MIDI) but do not yet "listen" reliably from audio. Our method and dataset make the perception-reasoning boundary explicit and offer actionable guidance for building robust, audio-first music systems.

cs.SD↗

arXiv2025

The MUSE Benchmark: Probing Music Perception and Auditory Relational Reasoning in Audio LLMS

Multimodal Large Language Models (MLLMs) have demonstrated capabilities in audio understanding, but current evaluations may obscure fundamental weaknesses in relational reasoning. We introduce the Music Understanding and Structural Evaluation (MUSE) Benchmark, an open-source resource with 10 tasks designed to probe fundamental music perception skills. We evaluate four SOTA models (Gemini Pro and Flash, Qwen2.5-Omni, and Audio-Flamingo 3) against a large human baseline (N=200). Our results reveal a wide variance in SOTA capabilities and a persistent gap with human experts. While Gemini Pro succeeds on basic perception, Qwen and Audio Flamingo 3 perform at or near chance, exposing severe perceptual deficits. Furthermore, we find Chain-of-Thought (CoT) prompting provides inconsistent, often detrimental results. Our work provides a critical tool for evaluating invariant musical representations and driving development of more robust AI systems.

cs.AI↗

arXiv2025

Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification

This paper presents the objective, dataset, baseline, and metrics of Task 3 of the DCASE2025 Challenge on sound event localization and detection (SELD). In previous editions, the challenge used four-channel audio formats of first-order Ambisonics (FOA) and microphone array. In contrast, this year's challenge investigates SELD with stereo audio data (termed stereo SELD). This change shifts the focus from more specialized 360° audio and audiovisual scene analysis to more commonplace audio and media scenarios with limited field-of-view (FOV). Due to inherent angular ambiguities in stereo audio data, the task focuses on direction-of-arrival (DOA) estimation in the azimuth plane (left-right axis) along with distance estimation. The challenge remains divided into two tracks: audio-only and audiovisual, with the audiovisual track introducing a new sub-task of onscreen/offscreen event classification necessitated by the limited FOV. This challenge introduces the DCASE2025 Task3 Stereo SELD Dataset, whose stereo audio and perspective video clips are sampled and converted from the STARSS23 recordings. The baseline system is designed to process stereo audio and corresponding video frames as inputs. In addition to the typical SELD event classification and localization, it integrates onscreen/offscreen classification for the audiovisual track. The evaluation metrics have been modified to introduce an onscreen/offscreen accuracy metric, which assesses the models' ability to identify which sound sources are onscreen. In the experimental evaluation, the baseline system performs reasonably well with the stereo audio data.

cs.SD↗

arXiv2025

Latent Acoustic Mapping for Direction of Arrival Estimation: A Self-Supervised Approach

Acoustic mapping techniques have long been used in spatial audio processing for direction of arrival estimation (DoAE). Traditional beamforming methods for acoustic mapping, while interpretable, often rely on iterative solvers that can be computationally intensive and sensitive to acoustic variability. On the other hand, recent supervised deep learning approaches offer feedforward speed and robustness but require large labeled datasets and lack interpretability. Despite their strengths, both methods struggle to consistently generalize across diverse acoustic setups and array configurations, limiting their broader applicability. We introduce the Latent Acoustic Mapping (LAM) model, a self-supervised framework that bridges the interpretability of traditional methods with the adaptability and efficiency of deep learning methods. LAM generates high-resolution acoustic maps, adapts to varying acoustic conditions, and operates efficiently across different microphone arrays. We assess its robustness on DoAE using the LOCATA and STARSS benchmarks. LAM achieves comparable or superior localization performance to existing supervised methods. Additionally, we show that LAM's acoustic maps can serve as effective features for supervised models, further enhancing DoAE accuracy and underscoring its potential to advance adaptive, high-performance sound localization systems.

cs.SD↗

arXiv2025

Spectrotemporal Modulation: Efficient and Interpretable Feature Representation for Classifying Speech, Music, and Environmental Sounds

Audio DNNs have demonstrated impressive performance on various machine listening tasks; however, most of their representations are computationally costly and uninterpretable, leaving room for optimization. Here, we propose a novel approach centered on spectrotemporal modulation (STM) features, a signal processing method that mimics the neurophysiological representation in the human auditory cortex. The classification performance of our STM-based model, without any pretraining, is comparable to that of pretrained audio DNNs across diverse naturalistic speech, music, and environmental sounds, which are essential categories for both human cognition and machine perception. These results show that STM is an efficient and interpretable feature representation for audio classification, advancing the development of machine listening and unlocking exciting new possibilities for basic understanding of speech and auditory sciences, as well as developing audio BCI and cognitive computing.

cs.SD↗

arXiv2025

Generating Diverse Audio-Visual 360 Soundscapes for Sound Event Localization and Detection

We present SELDVisualSynth, a tool for generating synthetic videos for audio-visual sound event localization and detection (SELD). Our approach incorporates real-world background images to improve realism in synthetic audio-visual SELD data while also ensuring audio-visual spatial alignment. The tool creates 360 synthetic videos where objects move matching synthetic SELD audio data and its annotations. Experimental results demonstrate that a model trained with this data attains performance gains across multiple metrics, achieving superior localization recall (56.4 LR) and competitive localization error (21.9deg LE). We open-source our data generation tool for maximal use by members of the SELD research community.

cs.SD↗

arXiv2025

Design and Implementation of the Transparent, Interpretable, and Multimodal (TIM) AR Personal Assistant

The concept of an AI assistant for task guidance is rapidly shifting from a science fiction staple to an impending reality. Such a system is inherently complex, requiring models for perceptual grounding, attention, and reasoning, an intuitive interface that adapts to the performer's needs, and the orchestration of data streams from many sensors. Moreover, all data acquired by the system must be readily available for post-hoc analysis to enable developers to understand performer behavior and quickly detect failures. We introduce TIM, the first end-to-end AI-enabled task guidance system in augmented reality which is capable of detecting both the user and scene as well as providing adaptable, just-in-time feedback. We discuss the system challenges and propose design solutions. We also demonstrate how TIM adapts to domain applications with varying needs, highlighting how the system components can be customized for each scenario.

cs.ET↗

arXiv2025

Guitar-TECHS: An Electric Guitar Dataset Covering Techniques, Musical Excerpts, Chords and Scales Using a Diverse Array of Hardware

Guitar-related machine listening research involves tasks like timbre transfer, performance generation, and automatic transcription. However, small datasets often limit model robustness due to insufficient acoustic diversity and musical content. To address these issues, we introduce Guitar-TECHS, a comprehensive dataset featuring a variety of guitar techniques, musical excerpts, chords, and scales. These elements are performed by diverse musicians across various recording settings. Guitar-TECHS incorporates recordings from two stereo microphones: an egocentric microphone positioned on the performer's head and an exocentric microphone placed in front of the performer. It also includes direct input recordings and microphoned amplifier outputs, offering a wide spectrum of audio inputs and recording qualities. All signals and MIDI labels are properly synchronized. Its multi-perspective and multi-modal content makes Guitar-TECHS a valuable resource for advancing data-driven guitar research, and to develop robust guitar listening algorithms. We provide empirical data to demonstrate the dataset's effectiveness in training robust models for Guitar Tablature Transcription.

cs.SD↗

arXiv2024

Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms

Sound event localization and detection (SELD) is an important task in machine listening. Major advancements rely on simulated data with sound events in specific rooms and strong spatio-temporal labels. SELD data is simulated by convolving spatialy-localized room impulse responses (RIRs) with sound waveforms to place sound events in a soundscape. However, RIRs require manual collection in specific rooms. We present SpatialScaper, a library for SELD data simulation and augmentation. Compared to existing tools, SpatialScaper emulates virtual rooms via parameters such as size and wall absorption. This allows for parameterized placement (including movement) of foreground and background sound sources. SpatialScaper also includes data augmentation pipelines that can be applied to existing SELD data. As a case study, we use SpatialScaper to add rooms to the DCASE SELD data. Training a model with our data led to progressive performance improves as a direct function of acoustic diversity. These results show that SpatialScaper is valuable to train robust SELD models.

eess.AS↗

arXiv2024

Robust DOA estimation using deep acoustic imaging

Direction of arrival estimation (DoAE) aims at tracking a sound in azimuth and elevation. Recent advancements include data-driven models with inputs derived from ambisonics intensity vectors or correlations between channels in a microphone array. A spherical intensity map (SIM), or acoustic image, is an alternative input representation that remains underexplored. SIMs benefit from high-resolution microphone arrays, yet most DoAE datasets use low-resolution ones. Therefore, we first propose a super-resolution method to upsample low-resolution microphones. Next, we benchmark DoAE models that use SIMs as input. We arrive to a model that uses SIMs for DoAE estimation and outperforms a baseline and a state-of-the-art model. Our study highlights the relevance of acoustic imaging for DoAE tasks.

cs.SD↗

arXiv2023

F0 analysis of Ghanaian pop singing reveals progressive alignment with equal temperament over the past three decades: a case study

Contemporary Ghanaian popular singing combines European and traditional Ghanaian influences. We hypothesize that access to technology embedded with equal temperament catalyzed a progressive alignment of Ghanaian singing with equal-tempered scales over time. To test this, we study the Ghanaian singer Daddy Lumba, whose work spans from the earliest Ghanaian electronic style in the late 1980s to the present. Studying a singular musician as a case study allows us to refine our analysis without over-interpreting the findings. We curated a collection of his songs, distributed between 1989 and 2016, to extract F0 values from isolated vocals. We used Gaussian mixture modeling (GMM) to approximate each song's scale and found that the pitch variance has been decreasing over time. We also determined whether the GMM components follow the arithmetic relationships observed in equal-tempered scales, and observed that Daddy Lumba's singing better aligns with equal temperament in recent years. Together, results reveal the impact of exposure to equal-tempered scales, resulting in lessened microtonal content in Daddy Lumba's singing. Our study highlights a potential vulnerability of Ghanaian musical scales and implies a need for research that maps and archives singing styles.

cs.SD↗

arXiv2023

Sound Source Distance Estimation in Diverse and Dynamic Acoustic Conditions

Localizing a moving sound source in the real world involves determining its direction-of-arrival (DOA) and distance relative to a microphone. Advancements in DOA estimation have been facilitated by data-driven methods optimized with large open-source datasets with microphone array recordings in diverse environments. In contrast, estimating a sound source's distance remains understudied. Existing approaches assume recordings by non-coincident microphones to use methods that are susceptible to differences in room reverberation. We present a CRNN able to estimate the distance of moving sound sources across multiple datasets featuring diverse rooms, outperforming a recently-published approach. We also characterize our model's performance as a function of sound source distance and different training losses. This analysis reveals optimal training using a loss that weighs model errors as an inverse function of the sound source true distance. Our study is the first to demonstrate that sound source distance estimation can be performed across diverse acoustic conditions using deep learning.

cs.SD↗