CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR

• URL: http://arxiv.org/abs/2502.20040v2
• Date: Wed, 30 Jul 2025 07:22:13 GMT
• Title: CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR
• Authors: Nian Shao, Rui Zhou, Pengyu Wang, Xian Li, Ying Fang, Yujie Yang, Xiaofei Li,
• Abstract summary: The proposed network takes as input the noisy and reverberant microphone recording and predicts the corresponding clean Mel-spectrogram.<n>The enhanced Mel-spectrogram can be either transformed to the speech waveform with a neural vocoder or directly used for ASR.
• Score: 36.77663840488492
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we propose CleanMel, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance. The proposed network takes as input the noisy and reverberant microphone recording and predicts the corresponding clean Mel-spectrogram. The enhanced Mel-spectrogram can be either transformed to the speech waveform with a neural vocoder or directly used for ASR. The proposed network is composed of interleaved cross-band and narrow-band processing in the Mel-frequency domain, for learning the full-band spectral pattern and the narrow-band properties of signals, respectively. Compared to linear-frequency domain or time-domain speech enhancement, the key advantage of Mel-spectrogram enhancement is that Mel-frequency presents speech in a more compact way and thus is easier to learn, which will benefit both speech quality and ASR. Experimental results on five English and one Chinese datasets demonstrate a significant improvement in both speech quality and ASR performance achieved by the proposed model.Code and audio examples of our model are available online.

Related papers

• NaturalL2S: End-to-End High-quality Multispeaker Lip-to-Speech Synthesis with Differential Digital Signal Processing [16.47490478732181]
  We propose an end-to-end framework integrating acoustic inductive biases with differentiable speech generation components.<n>Specifically, we introduce a fundamental frequency (F0) predictor to capture prosodic variations in synthesized speech.<n>Our approach achieves satisfactory performance on speaker similarity without explicitly modelling speaker characteristics.
  arXiv  Detail & Related papers  (2025-02-17T16:40:23Z)
• A Mel Spectrogram Enhancement Paradigm Based on CWT in Speech Synthesis [3.9940425551415597]
  We propose a Mel spectrogram enhancement paradigm based on the continuous wavelet transform (CWT) This paradigm introduces a more detailed wavelet spectrogram, which like the post-processing network takes as input the Mel spectrogram output by the decoder. The experimental results demonstrate that the speech synthesised using the model with the Mel spectrogram enhancement paradigm exhibits higher MOS, with an improvement of 0.14 and 0.09 compared to the baseline model, respectively.
  arXiv  Detail & Related papers  (2024-06-18T00:34:44Z)
• Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer [59.57249127943914]
  We present a multilingual Audio-Visual Speech Recognition model incorporating several enhancements to improve performance and audio noise robustness. We increase the amount of audio-visual training data for six distinct languages, generating automatic transcriptions of unlabelled multilingual datasets. Our proposed model achieves new state-of-the-art performance on the LRS3 dataset, reaching WER of 0.8%.
  arXiv  Detail & Related papers  (2024-03-14T01:16:32Z)
• Speech enhancement with frequency domain auto-regressive modeling [34.55703785405481]
  Speech applications in far-field real world settings often deal with signals that are corrupted by reverberation. We propose a unified framework of speech dereverberation for improving the speech quality and the automatic speech recognition (ASR) performance.
  arXiv  Detail & Related papers  (2023-09-24T03:25:51Z)
• Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder [58.523884148942166]
  We propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework. First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes. Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers.
  arXiv  Detail & Related papers  (2023-08-14T08:19:24Z)
• From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion [84.138804145918]
  Deep generative models can generate high-fidelity audio conditioned on various types of representations. These models are prone to generate audible artifacts when the conditioning is flawed or imperfect. We propose a high-fidelity multi-band diffusion-based framework that generates any type of audio modality from low-bitrate discrete representations.
  arXiv  Detail & Related papers  (2023-08-02T22:14:29Z)
• Towards Robust FastSpeech 2 by Modelling Residual Multimodality [4.4904382374090765]
  State-of-the-art non-autoregressive text-to-speech models based on FastSpeech 2 can efficiently synthesise high-fidelity and natural speech. We observe characteristic audio distortions in expressive speech datasets. TVC-GMM reduces spectrogram smoothness and improves perceptual audio quality in particular for expressive datasets.
  arXiv  Detail & Related papers  (2023-06-02T11:03:26Z)
• 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)
• R-MelNet: Reduced Mel-Spectral Modeling for Neural TTS [1.8927791081850118]
  This paper introduces R-MelNet, a two-part autoregressive architecture with a backend WaveRNN-style audio decoder. The model produces low-resolution mel-spectral features which are used by a WaveRNN decoder to produce an audio waveform.
  arXiv  Detail & Related papers  (2022-06-30T13:29:31Z)
• SVTS: Scalable Video-to-Speech Synthesis [105.29009019733803]
  We introduce a scalable video-to-speech framework consisting of two components: a video-to-spectrogram predictor and a pre-trained neural vocoder. We are the first to show intelligible results on the challenging LRS3 dataset.
  arXiv  Detail & Related papers  (2022-05-04T13:34:07Z)
• Audio-visual multi-channel speech separation, dereverberation and recognition [70.34433820322323]
  This paper proposes an audio-visual multi-channel speech separation, dereverberation and recognition approach. The advantage of the additional visual modality over using audio only is demonstrated on two neural dereverberation approaches. Experiments conducted on the LRS2 dataset suggest that the proposed audio-visual multi-channel speech separation, dereverberation and recognition system outperforms the baseline.
  arXiv  Detail & Related papers  (2022-04-05T04:16:03Z)
• Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition [52.71604809100364]
  We propose wav2vec-Switch, a method to encode noise robustness into contextualized representations of speech. Specifically, we feed original-noisy speech pairs simultaneously into the wav2vec 2.0 network. In addition to the existing contrastive learning task, we switch the quantized representations of the original and noisy speech as additional prediction targets.
  arXiv  Detail & Related papers  (2021-10-11T00:08:48Z)
• Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks [14.942060304734497]
  spatial clustering techniques can achieve significant multi-channel noise reduction across relatively arbitrary microphone configurations. LSTM neural networks have successfully been trained to recognize speech from noise on single-channel inputs, but have difficulty taking full advantage of the information in multi-channel recordings. This paper integrates these two approaches, training LSTM speech models to clean the masks generated by the Model-based EM Source Separation and Localization (MESSL) spatial clustering method.
  arXiv  Detail & Related papers  (2020-12-02T22:35:00Z)

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.