Improving generalizability of distilled self-supervised speech processing models under distorted settings

• URL: http://arxiv.org/abs/2210.07978v1
• Date: Fri, 14 Oct 2022 17:17:45 GMT
• Title: Improving generalizability of distilled self-supervised speech processing models under distorted settings
• Authors: Kuan-Po Huang, Yu-Kuan Fu, Tsu-Yuan Hsu, Fabian Ritter Gutierrez, Fan-Lin Wang, Liang-Hsuan Tseng, Yu Zhang, Hung-yi Lee
• Abstract summary: Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. This paper proposes to apply Cross-Distortion Mapping and Domain Adversarial Training to SSL models during knowledge distillation.
• Score: 46.503354111827356
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar performance as original SSL models, distilled counterparts suffer from performance degradation even more than their original versions in distorted environments. This paper proposes to apply Cross-Distortion Mapping and Domain Adversarial Training to SSL models during knowledge distillation to alleviate the performance gap caused by the domain mismatch problem. Results show consistent performance improvements under both in- and out-of-domain distorted setups for different downstream tasks while keeping efficient model size.

Related papers

• A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection [2.432576583937997]
  Spoof-SUPERB is a benchmark for audio deepfake detection.<n>We evaluate 20 SSL models spanning generative, discriminative, and spectrogram-based architectures.
  arXiv  Detail & Related papers  (2026-03-02T05:45:55Z)
• Position-invariant Fine-tuning of Speech Enhancement Models with Self-supervised Speech Representations [25.2377839206337]
  Front-end speech enhancement (SE) models with self-supervised learning (SSL)-based speech models are effective for downstream tasks in noisy conditions.<n>MSE is prone to exploiting positional embeddings in SSL models, allowing the objective to be minimised through positional correlations instead of content-related information.<n>This work frames the problem as a general limitation of self-supervised representation fine-tuning and investigates it through representation-guided SE.
  arXiv  Detail & Related papers  (2026-01-28T22:13:05Z)
• How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario [72.02391485962127]
  Speech Self-Supervised Learning (SSL) models achieve impressive performance on Automatic Speech Recognition (ASR) In low-resource language ASR, they encounter the domain mismatch problem between pre-trained and low-resource languages. We extend a conventional efficient fine-tuning scheme based on the adapter to handle these issues.
  arXiv  Detail & Related papers  (2024-11-27T10:51:00Z)
• ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets [106.7760874400261]
  This paper presents ML-SUPERB2.0, which is a new benchmark for evaluating pre-trained SSL and supervised speech models. We find performance improvements over the setup of ML-SUPERB, but performance depends on the downstream model design. Also, we find large performance differences between languages and datasets, suggesting the need for more targeted approaches.
  arXiv  Detail & Related papers  (2024-06-12T21:01:26Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training. It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models. While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• 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)
• Pushing the Limits of Unsupervised Unit Discovery for SSL Speech Representation [12.506633315768832]
  HuBERT is a successful example that utilizes offline clustering to convert speech features into discrete units for a masked language modeling pretext task. We present an unsupervised method to improve SSL targets. Two models are proposed, MonoBERT and PolyBERT, which leverage context-independent and context-dependent phoneme-based units for pre-training.
  arXiv  Detail & Related papers  (2023-06-15T07:45:12Z)
• Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations [30.293081541301746]
  Self-supervised learning (SSL) speech models such as wav2vec and HuBERT have demonstrated state-of-the-art performance on automatic speech recognition. We argue that the problem is caused by the lack of disentangled representations and an utterance-level learning objective. Our models outperform the current best model, WavLM, on all utterance-level non-semantic tasks on the SUPERB benchmark with only 20% of labeled data.
  arXiv  Detail & Related papers  (2023-05-14T08:26:24Z)
• Exploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition [5.802425107635222]
  Miniaturization for SSL models has become an important research direction of practical value. We explore the effective distillation of HuBERT-based SSL models for automatic speech recognition (ASR) A discriminative loss is introduced for HuBERT to enhance the distillation performance, especially in low-resource scenarios.
  arXiv  Detail & Related papers  (2022-10-27T17:21:14Z)
• Exploring Efficient-tuning Methods in Self-supervised Speech Models [53.633222197712875]
  Self-supervised learning can learn powerful representations for different speech tasks. In downstream tasks, the parameters of SSL models are frozen, and only the adapters are trained. We show that the performance parity can be achieved with over 90% parameter reduction.
  arXiv  Detail & Related papers  (2022-10-10T11:08:12Z)
• Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning [13.391307807956673]
  We propose a novel automatic pronunciation assessment method based on self-supervised learning (SSL) models. First, the proposed method fine-tunes the pre-trained SSL models with connectionist temporal classification to adapt the English pronunciation of English-as-a-second-language learners. We show that the proposed SSL model-based methods outperform the baselines, in terms of the Pearson correlation coefficient, on datasets of Korean ESL learner children and Speechocean762.
  arXiv  Detail & Related papers  (2022-04-08T06:13:55Z)
• Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation [60.26511271597065]
  Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when encountering speech distortions.
  arXiv  Detail & Related papers  (2022-03-30T07:25:52Z)
• Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding [76.89426311082927]
  Existing models are trained on clean data, which causes a textitgap between clean data training and real-world inference. We propose a method from the perspective of domain adaptation, by which both high- and low-quality samples are embedding into similar vector space. Experiments on the widely-used dataset, Snips, and large scale in-house dataset (10 million training examples) demonstrate that this method not only outperforms the baseline models on real-world (noisy) corpus but also enhances the robustness, that is, it produces high-quality results under a noisy environment.
  arXiv  Detail & Related papers  (2021-04-13T17:54:33Z)

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.