{"list":"other","total":53,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"2108.06209","title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","created":"2021-08-07","cited_by_count":347},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"2403.03100","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","created":"2024-03-05","cited_by_count":226},{"id":"2407.05361","title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","created":"2024-07-07","cited_by_count":204},{"id":"2208.05830","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","created":"2022-08-11","cited_by_count":197},{"id":"2104.09494","title":"NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets","created":"2021-04-19","cited_by_count":192},{"id":"2006.12847","title":"Real Time Speech Enhancement in the Waveform Domain","created":"2020-06-23","cited_by_count":186},{"id":"2110.01763","title":"DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors","created":"2021-10-05","cited_by_count":172},{"id":"2409.00750","title":"MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer","created":"2024-09-01","cited_by_count":161},{"id":"2005.11262","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","created":"2020-05-22","cited_by_count":155},{"id":"2105.02446","title":"DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism","created":"2021-05-06","cited_by_count":154},{"id":"2005.13981","title":"The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results","created":"2020-05-16","cited_by_count":133},{"id":"2010.11567","title":"AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines","created":"2020-10-22","cited_by_count":111},{"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":"1807.09840","title":"A multi-device dataset for urban acoustic scene classification","created":"2018-07-25","cited_by_count":75},{"id":"2209.04439","title":"Improved Masked Image Generation with Token-Critic","created":"2022-09-09","cited_by_count":64},{"id":"2308.06873","title":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer","created":"2023-08-14","cited_by_count":64},{"id":"2211.12433","title":"TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation","created":"2022-11-22","cited_by_count":63},{"id":"2104.01497","title":"Hi-Fi Multi-Speaker English TTS Dataset","created":"2021-04-03","cited_by_count":60},{"id":"2112.10358","title":"Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus","created":"2021-12-20","cited_by_count":60},{"id":"2310.16338","title":"Generative Pre-training for Speech with Flow Matching","created":"2023-10-25","cited_by_count":55},{"id":"2201.07429","title":"Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis","created":"2022-01-19","cited_by_count":53},{"id":"2309.07314","title":"AudioSR: Versatile Audio Super-resolution at Scale","created":"2023-09-13","cited_by_count":39},{"id":"2401.16812","title":"SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics","created":"2024-01-30","cited_by_count":38},{"id":"2204.05841","title":"VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration","created":"2022-04-12","cited_by_count":37},{"id":"2312.09747","title":"SELM: Speech Enhancement Using Discrete Tokens and Language Models","created":"2023-12-15","cited_by_count":36},{"id":"2203.07960","title":"Investigating self-supervised learning for speech enhancement and separation","created":"2022-03-15","cited_by_count":35},{"id":"2207.03546","title":"BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus","created":"2022-07-07","cited_by_count":32},{"id":"2009.06122","title":"ICASSP 2021 Deep Noise Suppression Challenge","created":"2020-09-14","cited_by_count":27},{"id":"2206.07293","title":"FRCRN: Boosting Feature Representation using Frequency Recurrence for Monaural Speech Enhancement","created":"2022-06-15","cited_by_count":26},{"id":"2204.03339","title":"Boosting Self-Supervised Embeddings for Speech Enhancement","created":"2022-04-07","cited_by_count":24},{"id":"2406.02092","title":"MaskSR: Masked Language Model for Full-band Speech Restoration","created":"2024-06-04","cited_by_count":24},{"id":"2008.06412","title":"Data augmentation and loss normalization for deep noise suppression","created":"2020-08-14","cited_by_count":23},{"id":"2011.03706","title":"ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration","created":"2020-11-07","cited_by_count":22},{"id":"1711.05747","title":"Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition","created":"2017-11-15","cited_by_count":19},{"id":"2406.04660","title":"URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement","created":"2024-06-07","cited_by_count":17},{"id":"2409.16117","title":"Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration","created":"2024-09-24","cited_by_count":16},{"id":"2202.13277","title":"Learning the Beauty in Songs: Neural Singing Voice Beautifier","created":"2022-02-27","cited_by_count":10},{"id":"2309.17384","title":"Toward Universal Speech Enhancement for Diverse Input Conditions","created":"2023-09-29","cited_by_count":10},{"id":"2409.07841","title":"TSELM: Target Speaker Extraction using Discrete Tokens and Language Models","created":"2024-09-12","cited_by_count":10},{"id":"2409.15799","title":"WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction","created":"2024-09-24","cited_by_count":8},{"id":"2401.09686","title":"An Empirical Study on the Impact of Positional Encoding in Transformer-based Monaural Speech Enhancement","created":"2024-01-18","cited_by_count":5},{"id":"2409.09357","title":"Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility","created":"2024-09-14","cited_by_count":5},{"id":"2111.11606","title":"Effect of noise suppression losses on speech distortion and ASR performance","created":"2021-11-23","cited_by_count":4},{"id":"2311.14490","title":"Overview Of The 2023 Icassp Sp Clarity Challenge: Speech Enhancement For Hearing Aids","created":"2023-11-24","cited_by_count":1}],"next_cursor":null}