Speech Enhancement

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

18 leaderboard tables shown for this task, 17 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 18 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

24 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

4 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 280 papers with code (982 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Proximal Policy Optimization Algorithms
  20 Jul 2017 188 repositories listed Syntology ran 99 of 176 samples · 77 unverified · 94 pointer-only (licence)
  We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using…
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
  27 Mar 2016 80 repositories listed Syntology ran 13 of 46 samples · 33 unverified · 5 pointer-only (licence)
  We consider image transformation problems, where an input image is transformed into an output image.
• SEGAN: Speech Enhancement Generative Adversarial Network
  28 Mar 2017 21 repositories listed Syntology ran 3 of 39 samples · 36 unverified · 4 pointer-only (licence)
  In contrast to current techniques, we operate at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are…
• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
  20 Sep 2018 17 repositories listed Syntology ran 7 of 36 samples · 29 unverified · 16 pointer-only (licence)
  The majority of the previous methods have formulated the separation problem through the time-frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase and magnitude…
• Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
  19 Jan 2020 13 repositories listed Syntology ran 1 of 16 samples · 15 unverified
  The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
• Phase-aware Speech Enhancement with Deep Complex U-Net
  7 Mar 2019 9 repositories listed Syntology ran 3 of 10 samples · 7 unverified · 2 pointer-only (licence)
  Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction.
• SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
  14 Oct 2021 6 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for…
• SoundStream: An End-to-End Neural Audio Codec
  7 Jul 2021 6 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 3 pointer-only (licence)
  We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs.
• FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement
  29 Oct 2020 6 repositories listed Syntology ran 1 of 21 samples · 20 unverified
  In our proposed FullSubNet, we connect a pure full-band model and a pure sub-band model sequentially and use practical joint training to integrate these two types of models' advantages.
• A Fully Convolutional Neural Network for Speech Enhancement
  22 Sep 2016 6 repositories listed
  In hearing aids, the presence of babble noise degrades hearing intelligibility of human speech greatly.
• WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement
  6 Apr 2020 5 repositories listed
  In WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the temporal sequential property of the locality feature is modeled by stacked simple recurrent units (SRU).
• MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement
  13 May 2019 5 repositories listed
  Adversarial loss in a conditional generative adversarial network (GAN) is not designed to directly optimize evaluation metrics of a target task, and thus, may not always guide the generator in a GAN to generate data…
• VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
  11 Oct 2018 5 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker.
• RNNoise-Ex: Hybrid Speech Enhancement System based on RNN and Spectral Features
  25 May 2021 4 repositories listed
  Recent interest in exploiting Deep Learning techniques for Noise Suppression, has led to the creation of Hybrid Denoising Systems that combine classic Signal Processing with Deep Learning.
• Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks
  31 Aug 2018 4 repositories listed
  Most methods of voice restoration for patients suffering from aphonia either produce whispered or monotone speech.
• HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement
  24 Mar 2022 3 repositories listed Syntology ran 9 of 12 samples · 3 unverified · 1 pointer-only (licence)
  Generative adversarial networks have recently demonstrated outstanding performance in neural vocoding outperforming best autoregressive and flow-based models.
• MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement
  8 Apr 2021 3 repositories listed Syntology ran 0 of 11 samples · 11 unverified
  The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory.
• Real Time Speech Enhancement in the Waveform Domain
  23 Jun 2020 3 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  The proposed model matches state-of-the-art performance of both causal and non causal methods while working directly on the raw waveform.
• Weighted Speech Distortion Losses for Neural-network-based Real-time Speech Enhancement
  12 Feb 2020 3 repositories listed
  This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement.
• Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models
  4 Nov 2019 3 repositories listed
  We present and release a new tool for music source separation with pre-trained models called Spleeter.
• rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method
  9 Jun 2019 3 repositories listed
  In the end, a posteriori SNR weighted energy difference is applied to the extended pitch segments of the denoised speech signal for detecting voice activity.
• Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices
  8 Mar 2019 3 repositories listed
  A popular approach to multichannel source separation is to integrate a spatial model with a source model for estimating the spatial covariance matrices (SCMs) and power spectral densities (PSDs) of each sound source in…
• Improved Speech Enhancement with the Wave-U-Net
  27 Nov 2018 3 repositories listed
  We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment.
• Language and Noise Transfer in Speech Enhancement Generative Adversarial Network
  18 Dec 2017 3 repositories listed
  In this work, we present the results of adapting a speech enhancement generative adversarial network by finetuning the generator with small amounts of data.
• MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
  1 Jul 2025 2 repositories listed
  Nevertheless, neither the concept of hybrid Mamba and time-frequency attention models nor their generalization performance have been explored for speech enhancement.
• SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios
  2 Oct 2024 2 repositories listed Syntology ran 8 of 11 samples · 3 unverified · 11 pointer-only (licence)
  Additionally, to investigate the differences between synthetic and real-world data, we selected 5 hours of raw, non-reverberant data from the SonicSet validation set and recorded a real-world speech separation dataset,…
• Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement
  30 Aug 2024 2 repositories listed
  Convolutional layers with 1-D filters are often used as frontend to encode audio signals.
• EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation
  10 Jun 2024 2 repositories listed Syntology ran 7 of 8 samples · 1 unverified
  We release the EARS (Expressive Anechoic Recordings of Speech) dataset, a high-quality speech dataset comprising 107 speakers from diverse backgrounds, totaling in 100 hours of clean, anechoic speech data.
• LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT
  7 Oct 2023 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  Previous mainstream audio-and-text LLMs use discrete audio tokens to represent both input and output audio; however, they suffer from performance degradation on tasks such as automatic speech recognition, speech-to-text…
• Multi-dimensional Speech Quality Assessment in Crowdsourcing
  14 Sep 2023 2 repositories listed
  The commonly used standard ITU-T Rec.

Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.