{"total":24,"rows":[{"id":"2301.02111","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","created":"2023-01-05","cited_by_count":752,"area":null},{"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,"area":null},{"id":"2101.01902","title":"Interspeech 2021 Deep Noise Suppression Challenge","created":"2021-01-06","cited_by_count":47,"area":null},{"id":"2110.06280","title":"S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations","created":"2021-10-12","cited_by_count":23,"area":null},{"id":"2110.05866","title":"MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech","created":"2021-10-12","cited_by_count":18,"area":null},{"id":"2207.04356","title":"A Comparative Study of Self-supervised Speech Representation Based Voice Conversion","created":"2022-07-10","cited_by_count":9,"area":null},{"id":"2402.12220","title":"Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2203.11562","title":"A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis","created":"2022-03-22","cited_by_count":5,"area":null},{"id":"2301.09099","title":"Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Study","created":"2023-01-22","cited_by_count":4,"area":null},{"id":"2107.09477","title":"On Prosody Modeling for ASR+TTS based Voice Conversion","created":"2021-07-20","cited_by_count":3,"area":null},{"id":"2410.22448","title":"A Closer Look at Neural Codec Resynthesis: Bridging the Gap between Codec and Waveform Generation","created":"2024-10-29","cited_by_count":3,"area":null},{"id":"2510.02187","title":"High-Fidelity Speech Enhancement via Discrete Audio Tokens","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2604.24416","title":"Scaling Properties of Continuous Diffusion Spoken Language Models","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2607.08111","title":"PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2608.30204","title":"When Models Hear What They Expect: Diagnosing Prosodic Heuristics in Multimodal Sarcasm Detection","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2109.09686","title":"Acoustic Echo Cancellation using Residual U-Nets","created":"2021-09-20","cited_by_count":0,"area":null},{"id":"2212.01911","title":"Speech MOS multi-task learning and rater bias correction","created":"2022-12-04","cited_by_count":0,"area":null},{"id":"2402.01413","title":"Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2403.14817","title":"Crowdsourced Multilingual Speech Intelligibility Testing","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2411.09066","title":"A multidimensional measurement of photorealistic avatar quality of experience","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2508.15860","title":"Robust Residual Finite Scalar Quantization for Neural Compression","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.24457","title":"Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2606.20137","title":"PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.29405","title":"Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}