FINALLY: fast and universal speech enhancement with studio-like quality

• URL: http://arxiv.org/abs/2410.05920v3
• Date: Thu, 31 Oct 2024 08:47:01 GMT
• Title: FINALLY: fast and universal speech enhancement with studio-like quality
• Authors: Nicholas Babaev, Kirill Tamogashev, Azat Saginbaev, Ivan Shchekotov, Hanbin Bae, Hosang Sung, WonJun Lee, Hoon-Young Cho, Pavel Andreev,
• Abstract summary: We address the challenge of speech enhancement in real-world recordings, which often contain various forms of distortion. We study various feature extractors for perceptual loss to facilitate the stability of adversarial training. We integrate WavLM-based perceptual loss into MS-STFT adversarial training pipeline, creating an effective and stable training procedure for the speech enhancement model.
• Score: 7.207284147264852
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper, we address the challenge of speech enhancement in real-world recordings, which often contain various forms of distortion, such as background noise, reverberation, and microphone artifacts. We revisit the use of Generative Adversarial Networks (GANs) for speech enhancement and theoretically show that GANs are naturally inclined to seek the point of maximum density within the conditional clean speech distribution, which, as we argue, is essential for the speech enhancement task. We study various feature extractors for perceptual loss to facilitate the stability of adversarial training, developing a methodology for probing the structure of the feature space. This leads us to integrate WavLM-based perceptual loss into MS-STFT adversarial training pipeline, creating an effective and stable training procedure for the speech enhancement model. The resulting speech enhancement model, which we refer to as FINALLY, builds upon the HiFi++ architecture, augmented with a WavLM encoder and a novel training pipeline. Empirical results on various datasets confirm our model's ability to produce clear, high-quality speech at 48 kHz, achieving state-of-the-art performance in the field of speech enhancement. Demo page: https://samsunglabs.github.io/FINALLY-page

Related papers

• Multi-modal Adversarial Training for Zero-Shot Voice Cloning [9.823246184635103]
  We propose a Transformer encoder-decoder architecture to conditionally discriminate between real and generated speech features. We introduce our novel adversarial training technique by applying it to a FastSpeech2 acoustic model and training on Libriheavy, a large multi-speaker dataset. Our model achieves improvements over the baseline in terms of speech quality and speaker similarity.
  arXiv  Detail & Related papers  (2024-08-28T16:30:41Z)
• SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks [94.10497337235083]
  We are first to explore the potential of prompting speech LMs in the domain of speech processing. We reformulate speech processing tasks into speech-to-unit generation tasks. We show that the prompting method can achieve competitive performance compared to the strong fine-tuning method.
  arXiv  Detail & Related papers  (2024-08-23T13:00:10Z)
• SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation [56.913182262166316]
  Chain-of-Information Generation (CoIG) is a method for decoupling semantic and perceptual information in large-scale speech generation. SpeechGPT-Gen is efficient in semantic and perceptual information modeling. It markedly excels in zero-shot text-to-speech, zero-shot voice conversion, and speech-to-speech dialogue.
  arXiv  Detail & Related papers  (2024-01-24T15:25:01Z)
• AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement [18.193191170754744]
  We introduce AV2Wav, a re-synthesis-based audio-visual speech enhancement approach. We use continuous rather than discrete representations to retain prosody and speaker information. Our approach outperforms a masking-based baseline in terms of both automatic metrics and a human listening test.
  arXiv  Detail & Related papers  (2023-09-14T21:07:53Z)
• LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders [53.30016986953206]
  We propose LA-VocE, a new two-stage approach that predicts mel-spectrograms from noisy audio-visual speech via a transformer-based architecture. We train and evaluate our framework on thousands of speakers and 11+ different languages, and study our model's ability to adapt to different levels of background noise and speech interference.
  arXiv  Detail & Related papers  (2022-11-20T15:27:55Z)
• Universal Speech Enhancement with Score-based Diffusion [21.294665965300922]
  We present a universal speech enhancement system that tackles 55 different distortions at the same time. Our approach consists of a generative model that employs score-based diffusion, together with a multi-resolution conditioning network. We show that this approach significantly outperforms the state of the art in a subjective test performed by expert listeners.
  arXiv  Detail & Related papers  (2022-06-07T07:32:32Z)
• Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis [67.73554826428762]
  We propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR. Our approach leverages audio-visual speech cues to generate the codes of a neural speech, enabling efficient synthesis of clean, realistic speech from noisy signals.
  arXiv  Detail & Related papers  (2022-03-31T17:57:10Z)
• A Training Framework for Stereo-Aware Speech Enhancement using Deep Neural Networks [34.012007729454815]
  We propose a novel stereo-aware framework for speech enhancement. The proposed framework is model independent, hence it can be applied to any deep learning based architecture. We show that by regularizing for an image preservation loss, the overall performance is improved, and the stereo aspect of the speech is better preserved.
  arXiv  Detail & Related papers  (2021-12-09T14:13:41Z)
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing [102.45426364965887]
  We propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM is built based on the HuBERT framework, with an emphasis on both spoken content modeling and speaker identity preservation. We scale up the training dataset from 60k hours to 94k hours of public audio data, and optimize its training procedure for better representation extraction.
  arXiv  Detail & Related papers  (2021-10-26T17:55:19Z)
• High Fidelity Speech Regeneration with Application to Speech Enhancement [96.34618212590301]
  We propose a wav-to-wav generative model for speech that can generate 24khz speech in a real-time manner. Inspired by voice conversion methods, we train to augment the speech characteristics while preserving the identity of the source.
  arXiv  Detail & Related papers  (2021-01-31T10:54:27Z)

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.