Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings

• URL: http://arxiv.org/abs/2509.03292v1
• Date: Wed, 03 Sep 2025 13:19:56 GMT
• Title: Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings
• Authors: Dyah A. M. G. Wisnu, Ryandhimas E. Zezario, Stefano Rini, Hsin-Min Wang, Yu Tsao,
• Abstract summary: We present a system for automatic multi-axis perceptual quality prediction of generative audio.<n>The task is to predict four Audio Aesthetic Scores--Production Quality, Production Complexity, Content Enjoyment, and Content Usefulness--for audio generated by text-to-speech (TTS), text-to-audio (TTA), and text-to-music (TTM) systems.
• Score: 32.813673146878685
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a system for automatic multi-axis perceptual quality prediction of generative audio, developed for Track 2 of the AudioMOS Challenge 2025. The task is to predict four Audio Aesthetic Scores--Production Quality, Production Complexity, Content Enjoyment, and Content Usefulness--for audio generated by text-to-speech (TTS), text-to-audio (TTA), and text-to-music (TTM) systems. A main challenge is the domain shift between natural training data and synthetic evaluation data. To address this, we combine BEATs, a pretrained transformer-based audio representation model, with a multi-branch long short-term memory (LSTM) predictor and use a triplet loss with buffer-based sampling to structure the embedding space by perceptual similarity. Our results show that this improves embedding discriminability and generalization, enabling domain-robust audio quality assessment without synthetic training data.

Related papers

• From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data [55.2480439325792]
  Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs.<n>These models are typically adapted from text-based large language models (LLMs) through additional training on audio-related tasks.<n>We propose a data generation framework that produces contrastive-like training data, designed to enhance ALLMs' ability to differentiate between present and absent sounds.
  arXiv  Detail & Related papers  (2025-05-26T16:08:41Z)
• Multi-Domain Audio Question Answering Toward Acoustic Content Reasoning in The DCASE 2025 Challenge [102.84031769492708]
  This task defines three QA subsets to test audio-language models on interactive question-answering over diverse acoustic scenes.<n>Preliminary results on the development set are compared, showing strong variation across models and subsets.<n>This challenge aims to advance the audio understanding and reasoning capabilities of audio-language models toward human-level acuity.
  arXiv  Detail & Related papers  (2025-05-12T09:04:16Z)
• ETTA: Elucidating the Design Space of Text-to-Audio Models [33.831803213869605]
  We study the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks.<n>We propose our best model dubbed Elucidated Text-To-Audio (ETTA)<n>ETTA provides improvements over the baselines trained on publicly available data, while being competitive with models trained on proprietary data.
  arXiv  Detail & Related papers  (2024-12-26T21:13:12Z)
• Developing an Effective Training Dataset to Enhance the Performance of AI-based Speaker Separation Systems [0.3277163122167434]
  We propose a novel method for constructing a realistic training set that includes mixture signals and corresponding ground truths for each speaker. We get a 1.65 dB improvement in Scale Invariant Signal to Distortion Ratio (SI-SDR) for speaker separation accuracy in realistic mixing.
  arXiv  Detail & Related papers  (2024-11-13T06:55:18Z)
• Leveraging Reverberation and Visual Depth Cues for Sound Event Localization and Detection with Distance Estimation [3.2472293599354596]
  This report describes our systems submitted for the DCASE2024 Task 3 challenge: Audio and Audiovisual Sound Event localization and Detection with Source Distance Estimation (Track B) Our main model is based on the audio-visual (AV) Conformer, which processes video and audio embeddings extracted with ResNet50 and with an audio encoder pre-trained on SELD, respectively. This model outperformed the audio-visual baseline of the development set of the STARSS23 dataset by a wide margin, halving its DOAE and improving the F1 by more than 3x.
  arXiv  Detail & Related papers  (2024-10-29T17:28:43Z)
• Where are we in audio deepfake detection? A systematic analysis over generative and detection models [59.09338266364506]
  SONAR is a synthetic AI-Audio Detection Framework and Benchmark.<n>It provides a comprehensive evaluation for distinguishing cutting-edge AI-synthesized auditory content.<n>It is the first framework to uniformly benchmark AI-audio detection across both traditional and foundation model-based detection systems.
  arXiv  Detail & Related papers  (2024-10-06T01:03:42Z)
• BATON: Aligning Text-to-Audio Model with Human Preference Feedback [21.369200033063752]
  The BATON framework is designed to enhance the alignment between generated audio and text prompt using human preference feedback. The experiment results demonstrate that our BATON can significantly improve the generation quality of the original text-to-audio models.
  arXiv  Detail & Related papers  (2024-02-01T16:39:47Z)
• MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition [62.89464258519723]
  We propose a multi-layer cross-attention fusion based AVSR approach that promotes representation of each modality by fusing them at different levels of audio/visual encoders. Our proposed approach surpasses the first-place system, establishing a new SOTA cpCER of 29.13% on this dataset.
  arXiv  Detail & Related papers  (2024-01-07T08:59:32Z)
• Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets [6.617487928813374]
  We present a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers. Our system ranked first in the 2023's DCASE Challenge, and it outperforms the current state of the art on the ClothoV2 benchmark by 5.6 pp. mAP@10.
  arXiv  Detail & Related papers  (2023-08-08T13:46:55Z)
• Self-Supervised Visual Acoustic Matching [63.492168778869726]
  Acoustic matching aims to re-synthesize an audio clip to sound as if it were recorded in a target acoustic environment. We propose a self-supervised approach to visual acoustic matching where training samples include only the target scene image and audio. Our approach jointly learns to disentangle room acoustics and re-synthesize audio into the target environment, via a conditional GAN framework and a novel metric.
  arXiv  Detail & Related papers  (2023-07-27T17:59:59Z)
• ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification [42.95038619688867]
  ASiT is a novel self-supervised learning framework that captures local and global contextual information by employing group masked model learning and self-distillation. We evaluate our pretrained models on both audio and speech classification tasks, including audio event classification, keyword spotting, and speaker identification.
  arXiv  Detail & Related papers  (2022-11-23T18:21:09Z)
• Fully Automated End-to-End Fake Audio Detection [57.78459588263812]
  This paper proposes a fully automated end-toend fake audio detection method. We first use wav2vec pre-trained model to obtain a high-level representation of the speech. For the network structure, we use a modified version of the differentiable architecture search (DARTS) named light-DARTS.
  arXiv  Detail & Related papers  (2022-08-20T06:46:55Z)

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.