Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables

• URL: http://arxiv.org/abs/2309.09220v2
• Date: Sat, 7 Sep 2024 13:20:47 GMT
• Title: Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables
• Authors: Ahmed Adel Attia, Yashish M. Siriwardena, Carol Espy-Wilson,
• Abstract summary: We study the impact of utilizing speech representations acquired via self-supervised learning (SSL) models. We also investigate the incorporation of novel tract variables (TVs) through an improved geometric transformation model. Our findings underscore the profound influence of rich feature representations from SSL models and improved geometric transformations with target TVs on the enhanced functionality of SI systems.
• Score: 2.048226951354646
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The performance of deep learning models depends significantly on their capacity to encode input features efficiently and decode them into meaningful outputs. Better input and output representation has the potential to boost models' performance and generalization. In the context of acoustic-to-articulatory speech inversion (SI) systems, we study the impact of utilizing speech representations acquired via self-supervised learning (SSL) models, such as HuBERT compared to conventional acoustic features. Additionally, we investigate the incorporation of novel tract variables (TVs) through an improved geometric transformation model. By combining these two approaches, we improve the Pearson product-moment correlation (PPMC) scores which evaluate the accuracy of TV estimation of the SI system from 0.7452 to 0.8141, a 6.9% increase. Our findings underscore the profound influence of rich feature representations from SSL models and improved geometric transformations with target TVs on the enhanced functionality of SI systems.

Related papers

• VQalAttent: a Transparent Speech Generation Pipeline based on Transformer-learned VQ-VAE Latent Space [0.49109372384514843]
  VQalAttent is a lightweight model designed to generate fake speech with tunable performance and interpretability. Our results demonstrate VQalAttent's capacity to generate intelligible speech samples with limited computational resources.
  arXiv  Detail & Related papers  (2024-11-22T00:21:39Z)
• Effective internal language model training and fusion for factorized transducer model [26.371223360905557]
  Internal language model (ILM) of the neural transducer has been widely studied. We propose a novel ILM training and decoding strategy for factorized transducer models.
  arXiv  Detail & Related papers  (2024-04-02T08:01:05Z)
• A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors [9.279391026742658]
  We analyze the effect of model size, training objectives, and model architecture on the models' performance as a feature extractor. We develop a novel metric, the Phonetic-Syntax Ratio (PSR), to measure the phonetic and synthetic information in the extracted representations.
  arXiv  Detail & Related papers  (2023-11-27T15:58:28Z)
• CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration [59.48235003469116]
  We show that data augmentation consistently enhances OOD performance. We also show that CF augmented models which are easier to calibrate also exhibit much lower entropy when assigning importance.
  arXiv  Detail & Related papers  (2023-09-14T16:16:40Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)
• Adaptive re-calibration of channel-wise features for Adversarial Audio Classification [0.0]
  We propose a recalibration of features using attention feature fusion for synthetic speech detection. We compare its performance against different detection methods including End2End models and Resnet-based models. We also demonstrate that the combination of Linear frequency cepstral coefficients (LFCC) and Mel Frequency cepstral coefficients (MFCC) using the attentional feature fusion technique creates better input features representations.
  arXiv  Detail & Related papers  (2022-10-21T04:21:56Z)
• Automatic Learning of Subword Dependent Model Scales [50.105894487730545]
  We show that the model scales for a combination of attention encoder-decoder acoustic model and language model can be learned as effectively as with manual tuning. We extend this approach to subword dependent model scales which could not be tuned manually which leads to 7% improvement on LBS and 3% on SWB.
  arXiv  Detail & Related papers  (2021-10-18T13:48:28Z)
• Factorized Neural Transducer for Efficient Language Model Adaptation [51.81097243306204]
  We propose a novel model, factorized neural Transducer, by factorizing the blank and vocabulary prediction. It is expected that this factorization can transfer the improvement of the standalone language model to the Transducer for speech recognition. We demonstrate that the proposed factorized neural Transducer yields 15% to 20% WER improvements when out-of-domain text data is used for language model adaptation.
  arXiv  Detail & Related papers  (2021-09-27T15:04:00Z)
• Improving Perceptual Quality by Phone-Fortified Perceptual Loss using Wasserstein Distance for Speech Enhancement [23.933935913913043]
  We propose a phone-fortified perceptual loss (PFPL) that takes phonetic information into account for training SE models. To effectively incorporate the phonetic information, the PFPL is computed based on latent representations of the wav2vec model. Our experimental results first reveal that the PFPL is more correlated with the perceptual evaluation metrics, as compared to signal-level losses.
  arXiv  Detail & Related papers  (2020-10-28T18:34:28Z)
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion [57.65753150356411]
  Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. We propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR) We argue that VC models with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech.
  arXiv  Detail & Related papers  (2020-08-07T11:02:07Z)
• Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement [102.48582597586233]
  We present a U-Net based attention model, U-Net$_At$, to enhance adversarial speech signals. We conduct experiments on the automatic speech recognition (ASR) task with adversarial audio attacks.
  arXiv  Detail & Related papers  (2020-03-31T02:16:34Z)

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.