Déréverbération non-supervisée de la parole par modèle hybride

• URL: http://arxiv.org/abs/2510.09025v1
• Date: Fri, 10 Oct 2025 05:51:17 GMT
• Title: Déréverbération non-supervisée de la parole par modèle hybride
• Abstract summary: Our approach uses limited acoustic information, like the reverberation time (RT60), to train a dereverberation system.<n> Experimental results demonstrate that our method achieves more consistent performance across various objective metrics than the state-of-the-art.
• Score: 26.82558286573733
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces a new training strategy to improve speech dereverberation systems in an unsupervised manner using only reverberant speech. Most existing algorithms rely on paired dry/reverberant data, which is difficult to obtain. Our approach uses limited acoustic information, like the reverberation time (RT60), to train a dereverberation system. Experimental results demonstrate that our method achieves more consistent performance across various objective metrics than the state-of-the-art.

Related papers

• A Hybrid Model for Weakly-Supervised Speech Dereverberation [2.731944614640173]
  This paper introduces a new training strategy to improve speech dereverberation systems using minimal acoustic information and reverberant (wet) speech.<n> Experimental results demonstrate that our method achieves more consistent performance across various objective metrics used in speech dereverberation than the state-of-the-art.
  arXiv  Detail & Related papers  (2025-02-06T09:21:22Z)
• Diffusion-based speech enhancement with a weighted generative-supervised learning loss [0.0]
  Diffusion-based generative models have recently gained attention in speech enhancement (SE) We propose augmenting the original diffusion training objective with a mean squared error (MSE) loss, measuring the discrepancy between estimated enhanced speech and ground-truth clean speech.
  arXiv  Detail & Related papers  (2023-09-19T09:13:35Z)
• Contextual-Utterance Training for Automatic Speech Recognition [65.4571135368178]
  We propose a contextual-utterance training technique which makes use of the previous and future contextual utterances. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. The proposed technique is able to reduce both the WER and the average last token emission latency by more than 6% and 40ms relative.
  arXiv  Detail & Related papers  (2022-10-27T08:10:44Z)
• Speech Enhancement and Dereverberation with Diffusion-based Generative Models [14.734454356396157]
  We present a detailed overview of the diffusion process that is based on a differential equation. We show that this procedure enables using only 30 diffusion steps to generate high-quality clean speech estimates. In an extensive cross-dataset evaluation, we show that the improved method can compete with recent discriminative models.
  arXiv  Detail & Related papers  (2022-08-11T13:55:12Z)
• Learning Phone Recognition from Unpaired Audio and Phone Sequences Based on Generative Adversarial Network [58.82343017711883]
  This paper investigates how to learn directly from unpaired phone sequences and speech utterances. GAN training is adopted in the first stage to find the mapping relationship between unpaired speech and phone sequence. In the second stage, another HMM model is introduced to train from the generator's output, which boosts the performance.
  arXiv  Detail & Related papers  (2022-07-29T09:29:28Z)
• On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training [33.79711018198589]
  We extend the existing mixture invariant training criterion to exploit both unpaired clean speech and real noisy data. It is found that the unpaired clean speech is crucial to improve quality of separated speech from real noisy speech. The proposed method also performs remixing of processed and unprocessed signals to alleviate the processing artifacts.
  arXiv  Detail & Related papers  (2022-05-03T19:37:58Z)
• Curriculum optimization for low-resource speech recognition [4.803994937990389]
  We propose an automated curriculum learning approach to optimize the sequence of training examples. We introduce a new difficulty measure called compression ratio that can be used as a scoring function for raw audio in various noise conditions.
  arXiv  Detail & Related papers  (2022-02-17T19:47:50Z)
• Sequence-level self-learning with multiple hypotheses [53.04725240411895]
  We develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR) In contrast to conventional unsupervised learning approaches, we adopt the emphmulti-task learning (MTL) framework. Our experiment results show that our method can reduce the WER on the British speech data from 14.55% to 10.36% compared to the baseline model trained with the US English data only.
  arXiv  Detail & Related papers  (2021-12-10T20:47:58Z)
• Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction [109.44933866397123]
  Noise robustness is essential for deploying automatic speech recognition systems in real-world environments. We employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We achieve comparable performance to the best supervised approach reported with only 16% of labeled data.
  arXiv  Detail & Related papers  (2021-10-28T20:39:02Z)
• Robust Imitation Learning from Noisy Demonstrations [81.67837507534001]
  We show that robust imitation learning can be achieved by optimizing a classification risk with a symmetric loss. We propose a new imitation learning method that effectively combines pseudo-labeling with co-training. Experimental results on continuous-control benchmarks show that our method is more robust compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-20T10:41:37Z)
• Segment Aggregation for short utterances speaker verification using raw waveforms [47.41124427552161]
  We propose a method that compensates for the performance degradation of speaker verification for short utterances. The proposed method adopts an ensemble-based design to improve the stability and accuracy of speaker verification systems.
  arXiv  Detail & Related papers  (2020-05-07T08:57:22Z)

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.