{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2208.05830","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","created":"2022-08-11","cited_by_count":197},{"id":"2006.12847","title":"Real Time Speech Enhancement in the Waveform Domain","created":"2020-06-23","cited_by_count":186},{"id":"2010.13154","title":"Attention is All You Need in Speech Separation","created":"2020-10-25","cited_by_count":185},{"id":"1910.06379","title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","created":"2019-10-14","cited_by_count":182},{"id":"1703.09452","title":"SEGAN: Speech Enhancement Generative Adversarial Network","created":"2017-03-28","cited_by_count":166},{"id":"2008.00264","title":"DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement","created":"2020-08-01","cited_by_count":141},{"id":"2202.05256","title":"Conditional Diffusion Probabilistic Model for Speech Enhancement","created":"2022-02-10","cited_by_count":132},{"id":"2104.03538","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","created":"2021-04-08","cited_by_count":114},{"id":"2212.11851","title":"StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation","created":"2022-12-22","cited_by_count":105},{"id":"1905.04874","title":"MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement","created":"2019-05-13","cited_by_count":104},{"id":"2203.17004","title":"Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain","created":"2022-03-31","cited_by_count":102},{"id":"2405.06573","title":"An Investigation of Incorporating Mamba for Speech Enhancement","created":"2024-05-10","cited_by_count":62},{"id":"2405.12609","title":"Mamba in Speech: Towards an Alternative to Self-Attention","created":"2024-05-21","cited_by_count":60},{"id":"2407.00463","title":"Open-Source Conversational AI with SpeechBrain 1.0","created":"2024-06-29","cited_by_count":56},{"id":"2305.13686","title":"MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra","created":"2023-05-23","cited_by_count":52},{"id":"1706.07162","title":"A Wavenet for Speech Denoising","created":"2017-06-22","cited_by_count":47},{"id":"2203.15149","title":"CMGAN: Conformer-based Metric GAN for Speech Enhancement","created":"2022-03-28","cited_by_count":45},{"id":"2403.18257","title":"Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation","created":"2024-03-27","cited_by_count":45},{"id":"2204.05841","title":"VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration","created":"2022-04-12","cited_by_count":37},{"id":"2405.11831","title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","created":"2024-05-20","cited_by_count":37},{"id":"2406.03344","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","created":"2024-06-05","cited_by_count":37},{"id":"2103.09963","title":"TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain","created":"2021-03-18","cited_by_count":36},{"id":"2403.07675","title":"Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers","created":"2024-03-12","cited_by_count":28},{"id":"2406.06086","title":"RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection","created":"2024-06-10","cited_by_count":27},{"id":"2407.09732","title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","created":"2024-07-13","cited_by_count":23},{"id":"2406.02178","title":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","created":"2024-06-04","cited_by_count":19},{"id":"2409.07273","title":"Rethinking Mamba in Speech Processing by Self-Supervised Models","created":"2024-09-11","cited_by_count":11},{"id":"2206.11703","title":"Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes","created":"2022-06-23","cited_by_count":10},{"id":"2405.13636","title":"Audio Mamba: Pretrained Audio State Space Model For Audio Tagging","created":"2024-05-22","cited_by_count":10},{"id":"2409.09337","title":"Wave-U-Mamba: An End-To-End Framework For High-Quality And Efficient Speech Super Resolution","created":"2024-09-14","cited_by_count":9},{"id":"2105.12831","title":"Self-attending RNN for Speech Enhancement to Improve Cross-corpus Generalization","created":"2021-05-26","cited_by_count":8},{"id":"2208.08082","title":"A Hybrid SFANC-FxNLMS Algorithm for Active Noise Control based on Deep Learning","created":"2022-08-17","cited_by_count":7},{"id":"2309.10457","title":"Diffusion-based speech enhancement with a weighted generative-supervised learning loss","created":"2023-09-19","cited_by_count":7},{"id":"2408.05057","title":"SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation","created":"2024-08-09","cited_by_count":6},{"id":"2410.13599","title":"GAN-Based Speech Enhancement for Low SNR Using Latent Feature Conditioning","created":"2024-10-17","cited_by_count":6},{"id":"2504.09381","title":"DiTSE: High-Fidelity Generative Speech Enhancement via Latent Diffusion Transformers","created":"2025-04-13","cited_by_count":6},{"id":"2303.05788","title":"Deep Generative Fixed-filter Active Noise Control","created":"2023-03-10","cited_by_count":5},{"id":"2409.05034","title":"TF-Mamba: A Time-Frequency Network for Sound Source Localization","created":"2024-09-08","cited_by_count":5},{"id":"2208.09997","title":"Spatially Selective Active Noise Control Systems","created":"2022-08-22","cited_by_count":4},{"id":"2211.04346","title":"Cross-Attention is all you need: Real-Time Streaming Transformers for Personalised Speech Enhancement","created":"2022-11-08","cited_by_count":3},{"id":"2402.09460","title":"Unsupervised learning based end-to-end delayless generative fixed-filter active noise control","created":"2024-02-08","cited_by_count":3},{"id":"2406.11401","title":"An Exploration of Length Generalization in Transformer-Based Speech Enhancement","created":"2024-06-17","cited_by_count":2},{"id":"2502.01185","title":"Deep Active Speech Cancellation with Mamba-Masking Network","created":"2025-02-03","cited_by_count":2},{"id":"2106.13754","title":"Nonlinear Acoustic Echo Cancellation with Deep Learning","created":"2021-06-25","cited_by_count":1}],"next_cursor":null}