Listenable Maps for Zero-Shot Audio Classifiers

• URL: http://arxiv.org/abs/2405.17615v1
• Date: Mon, 27 May 2024 19:25:42 GMT
• Title: Listenable Maps for Zero-Shot Audio Classifiers
• Authors: Francesco Paissan, Luca Della Libera, Mirco Ravanelli, Cem Subakan,
• Abstract summary: We introduce LMAC-Z (Listenable Maps for Audio) for the first time in the Zero-Shot context. We show that our method produces meaningful explanations that correlate well with different text prompts.
• Score: 12.446324804274628
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interpreting the decisions of deep learning models, including audio classifiers, is crucial for ensuring the transparency and trustworthiness of this technology. In this paper, we introduce LMAC-ZS (Listenable Maps for Audio Classifiers in the Zero-Shot context), which, to the best of our knowledge, is the first decoder-based post-hoc interpretation method for explaining the decisions of zero-shot audio classifiers. The proposed method utilizes a novel loss function that maximizes the faithfulness to the original similarity between a given text-and-audio pair. We provide an extensive evaluation using the Contrastive Language-Audio Pretraining (CLAP) model to showcase that our interpreter remains faithful to the decisions in a zero-shot classification context. Moreover, we qualitatively show that our method produces meaningful explanations that correlate well with different text prompts.

Related papers

• CLAIR-A: Leveraging Large Language Models to Judge Audio Captions [73.51087998971418]
  evaluating machine-generated audio captions is a complex task that requires considering diverse factors. We propose CLAIR-A, a simple and flexible method that leverages the zero-shot capabilities of large language models. In our evaluations, CLAIR-A better predicts human judgements of quality compared to traditional metrics.
  arXiv  Detail & Related papers  (2024-09-19T17:59:52Z)
• Learning Speech Representation From Contrastive Token-Acoustic Pretraining [57.08426714676043]
  We propose "Contrastive Token-Acoustic Pretraining (CTAP)", which uses two encoders to bring phoneme and speech into a joint multimodal space. The proposed CTAP model is trained on 210k speech and phoneme pairs, achieving minimally-supervised TTS, VC, and ASR.
  arXiv  Detail & Related papers  (2023-09-01T12:35:43Z)
• Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversion [35.23123094710891]
  We propose a high-similarity any-to-one voice conversion method with the input of SSL representations. Experimental results show that our proposed method achieves comparable similarity and higher naturalness than the supervised method.
  arXiv  Detail & Related papers  (2023-05-16T04:52:29Z)
• Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization [2.423660247459463]
  This paper tackles two major problem settings for interpretability of audio processing networks. For post-hoc interpretation, we aim to interpret decisions of a network in terms of high-level audio objects that are also listenable for the end-user. We propose a novel interpreter design that incorporates non-negative matrix factorization (NMF)
  arXiv  Detail & Related papers  (2023-05-11T20:50:51Z)
• Zero-shot text-to-speech synthesis conditioned using self-supervised speech representation model [13.572330725278066]
  A novel point of the proposed method is the direct use of the SSL model to obtain embedding vectors from speech representations trained with a large amount of data. The disentangled embeddings will enable us to achieve better reproduction performance for unseen speakers and rhythm transfer conditioned by different speeches.
  arXiv  Detail & Related papers  (2023-04-24T10:15:58Z)
• Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion [34.139871476234205]
  We investigate zero-shot voice conversion from a novel perspective of self-supervised disentangled speech representation learning. A zero-shot voice conversion is performed by feeding an arbitrary speaker embedding and content embeddings to a sequential variational autoencoder (VAE) decoder. On TIMIT and VCTK datasets, we achieve state-of-the-art performance on both objective evaluation, i.e., speaker verification (SV) on speaker embedding and content embedding, and subjective evaluation, i.e. voice naturalness and similarity, and remains to be robust even with noisy source/target utterances.
  arXiv  Detail & Related papers  (2022-03-30T23:03:19Z)
• Self-Supervised Learning for speech recognition with Intermediate layer supervision [52.93758711230248]
  We propose Intermediate Layer Supervision for Self-Supervised Learning (ILS-SSL) ILS-SSL forces the model to concentrate on content information as much as possible by adding an additional SSL loss on the intermediate layers. Experiments on LibriSpeech test-other set show that our method outperforms HuBERT significantly.
  arXiv  Detail & Related papers  (2021-12-16T10:45:05Z)
• Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information [55.75018546938499]
  We propose the speaker embedding-aware neural diarization (SEND) method, which predicts the power set encoded labels. Our method achieves lower diarization error rate than the target-speaker voice activity detection.
  arXiv  Detail & Related papers  (2021-11-28T12:51:04Z)
• VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion [54.29557210925752]
  One-shot voice conversion can be effectively achieved by speech representation disentanglement. We employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training. Experimental results reflect the superiority of the proposed method in learning effective disentangled speech representations.
  arXiv  Detail & Related papers  (2021-06-18T13:50:38Z)
• Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text [69.55642178336953]
  We present an approach to unsupervised audio representation learning. Based on a triplet neural network architecture, we harnesses semantically related cross-modal information to estimate audio track-relatedness. We show that our approach is invariant to the variety of annotation styles as well as to the different languages of this collection.
  arXiv  Detail & Related papers  (2020-03-27T07:37:15Z)
• Statistical Context-Dependent Units Boundary Correction for Corpus-based Unit-Selection Text-to-Speech [1.4337588659482519]
  We present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker adaptation, we aim to use only context dependent characteristics extrapolated with linguistic analysis techniques.
  arXiv  Detail & Related papers  (2020-03-05T12:42:13Z)

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.