Prosody-Guided Harmonic Attention for Phase-Coherent Neural Vocoding in the Complex Spectrum

• URL: http://arxiv.org/abs/2601.14472v1
• Date: Tue, 20 Jan 2026 20:53:24 GMT
• Title: Prosody-Guided Harmonic Attention for Phase-Coherent Neural Vocoding in the Complex Spectrum
• Authors: Mohammed Salah Al-Radhi, Riad Larbi, Mátyás Bartalis, Géza Németh,
• Abstract summary: We introduce prosody-guided harmonic attention to enhance voiced segment encoding and directly predict complex spectral components for waveform synthesis via inverse STFT.<n>Experiments on benchmark datasets demonstrate consistent gains over HiFi-GAN and AutoVocoder: F0 RMSE reduced by 22 percent, voiced/unvoiced error lowered by 18 percent, and MOS scores improved by 0.15.<n>These results show that prosody-guided attention combined with direct complex spectrum modeling yields more natural, pitch-accurate, and robust synthetic speech, setting a strong foundation for expressive neural vocoding.
• Score: 1.3066182802188198
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural vocoders are central to speech synthesis; despite their success, most still suffer from limited prosody modeling and inaccurate phase reconstruction. We propose a vocoder that introduces prosody-guided harmonic attention to enhance voiced segment encoding and directly predicts complex spectral components for waveform synthesis via inverse STFT. Unlike mel-spectrogram-based approaches, our design jointly models magnitude and phase, ensuring phase coherence and improved pitch fidelity. To further align with perceptual quality, we adopt a multi-objective training strategy that integrates adversarial, spectral, and phase-aware losses. Experiments on benchmark datasets demonstrate consistent gains over HiFi-GAN and AutoVocoder: F0 RMSE reduced by 22 percent, voiced/unvoiced error lowered by 18 percent, and MOS scores improved by 0.15. These results show that prosody-guided attention combined with direct complex spectrum modeling yields more natural, pitch-accurate, and robust synthetic speech, setting a strong foundation for expressive neural vocoding.

Related papers

• WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition [61.3530659856013]
  We propose a novel decoder architecture, WaveSeg, which jointly optimize feature refinement in spatial and wavelet domains.<n>High-frequency components are first learned from input images as explicit priors to reinforce boundary details.<n>Experiments on standard benchmarks demonstrate that WaveSeg, leveraging wavelet-domain frequency prior with Mamba-based attention, consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-10-24T01:41:31Z)
• UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching [20.92242470770289]
  We present a framework for audio super-resolution that employs a flow matching generative model to capture the conditional distribution of complex-valued spectral coefficients.<n> Experiments show that our model consistently produces high-fidelity 48 kHz audio across diverse upsampling factors.
  arXiv  Detail & Related papers  (2025-10-01T11:04:53Z)
• WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching [1.6385815610837167]
  WaveFM is a flow matching model for mel-spectrogram conditioned speech synthesis.<n>Our model achieves superior performance in both quality and efficiency compared to previous diffusion vocoders.
  arXiv  Detail & Related papers  (2025-03-20T20:17:17Z)
• SiFiSinger: A High-Fidelity End-to-End Singing Voice Synthesizer based on Source-filter Model [31.280358048556444]
  This paper presents an advanced end-to-end singing voice synthesis (SVS) system based on the source-filter mechanism. The proposed system also incorporates elements like the fundamental pitch (F0) predictor and waveform generation decoder. Experiments on the Opencpop dataset demonstrate efficacy of the proposed model in intonation quality and accuracy.
  arXiv  Detail & Related papers  (2024-10-16T13:18:45Z)
• 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)
• 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)
• SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping [51.698273019061645]
  SpecGrad adapts the diffusion noise so that its time-varying spectral envelope becomes close to the conditioning log-mel spectrogram. It is processed in the time-frequency domain to keep the computational cost almost the same as the conventional DDPM-based neural vocoders.
  arXiv  Detail & Related papers  (2022-03-31T02:08:27Z)
• Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem [65.25725367771075]
  This study demonstrates, for the first time, that the synthesis-based approach can also perform well on this problem. Specifically, we propose a novel speech separation/enhancement model based on the recognition of discrete symbols. By utilizing the synthesis model with the input of discrete symbols, after the prediction of discrete symbol sequence, each target speech could be re-synthesized.
  arXiv  Detail & Related papers  (2021-12-17T08:35:40Z)
• DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis [53.19363127760314]
  DiffSinger is a parameterized Markov chain which iteratively converts the noise into mel-spectrogram conditioned on the music score. The evaluations conducted on the Chinese singing dataset demonstrate that DiffSinger outperforms state-of-the-art SVS work with a notable margin.
  arXiv  Detail & Related papers  (2021-05-06T05:21:42Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

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.