{"total":61,"rows":[{"id":"2409.09305","title":"The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech","created":"2024-09-14","cited_by_count":83,"area":null},{"id":"2309.07937","title":"Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks","created":"2023-09-14","cited_by_count":72,"area":null},{"id":"2111.02363","title":"Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features","created":"2021-11-03","cited_by_count":33,"area":null},{"id":"2306.14422","title":"The Singing Voice Conversion Challenge 2023","created":"2023-06-26","cited_by_count":25,"area":null},{"id":"2501.17202","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","created":"2025-01-27","cited_by_count":25,"area":null},{"id":"2110.09103","title":"LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech","created":"2021-10-18","cited_by_count":24,"area":null},{"id":"2212.04559","title":"SpeechLMScore: Evaluating speech generation using speech language model","created":"2022-12-08","cited_by_count":20,"area":null},{"id":"2204.03040","title":"SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis","created":"2022-04-06","cited_by_count":18,"area":null},{"id":"2409.16644","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","created":"2024-09-25","cited_by_count":13,"area":null},{"id":"2204.04855","title":"Fusion of Self-supervised Learned Models for MOS Prediction","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2210.06324","title":"SQuId: Measuring Speech Naturalness in Many Languages","created":"2022-10-12","cited_by_count":10,"area":null},{"id":"2111.02585","title":"InQSS: a speech intelligibility and quality assessment model using a multi-task learning network","created":"2021-11-04","cited_by_count":7,"area":null},{"id":"2204.03219","title":"DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores","created":"2022-04-07","cited_by_count":7,"area":null},{"id":"2306.10493","title":"MOSPC: MOS Prediction Based on Pairwise Comparison","created":"2023-06-18","cited_by_count":7,"area":null},{"id":"2407.05608","title":"A Benchmark for Multi-speaker Anonymization","created":"2024-07-08","cited_by_count":7,"area":null},{"id":"2604.25937","title":"SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment","created":"2026-04-16","cited_by_count":7,"area":null},{"id":"2204.03310","title":"MTI-Net: A Multi-Target Speech Intelligibility Prediction Model","created":"2022-04-07","cited_by_count":6,"area":null},{"id":"2408.09300","title":"Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model","created":"2024-08-17","cited_by_count":6,"area":null},{"id":"2307.05132","title":"On the Use of Self-Supervised Speech Representations in Spontaneous Speech Synthesis","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2309.09548","title":"Non-Intrusive Speech Intelligibility Prediction for Hearing Aids using Whisper and Metadata","created":"2023-09-18","cited_by_count":4,"area":null},{"id":"2303.02719","title":"A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS","created":"2023-03-05","cited_by_count":3,"area":null},{"id":"2305.19396","title":"Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2307.13423","title":"Non Intrusive Intelligibility Predictor for Hearing Impaired Individuals using Self Supervised Speech Representations","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2310.00706","title":"Evaluating Speech Synthesis by Training Recognizers on Synthetic Speech","created":"2023-10-01","cited_by_count":3,"area":null},{"id":"2401.18045","title":"SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition","created":"2024-01-31","cited_by_count":3,"area":null},{"id":"2508.08957","title":"QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2206.13272","title":"Wideband Audio Waveform Evaluation Networks: Efficient, Accurate Estimation of Speech Qualities","created":"2022-06-27","cited_by_count":2,"area":null},{"id":"2211.00342","title":"Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features","created":"2022-11-01","cited_by_count":2,"area":null},{"id":"2306.09979","title":"Evaluation of Speech Representations for MOS prediction","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2306.12040","title":"Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selection","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2403.14808","title":"A Collection of Pragmatic-Similarity Judgments over Spoken Dialog Utterances","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2504.20447","title":"APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speech","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2508.21407","title":"DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2601.18281","title":"Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2209.06358","title":"Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset","created":"2022-09-14","cited_by_count":1,"area":null},{"id":"2308.09262","title":"Multi-Task Pseudo-Label Learning for Non-Intrusive Speech Quality Assessment Model","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2406.08445","title":"SVSNet+: Enhancing Speaker Voice Similarity Assessment Models with Representations from Speech Foundation Models","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2507.11636","title":"JSQA: Speech Quality Assessment with Perceptually-Inspired Contrastive Pretraining Based on JND Audio Pairs","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2509.03292","title":"Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2603.11482","title":"AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2204.11030","title":"Improving Self-Supervised Learning-based MOS Prediction Networks","created":"2022-04-23","cited_by_count":0,"area":null},{"id":"2206.13817","title":"Comparison of Speech Representations for the MOS Prediction System","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2210.14406","title":"RedPen: Region- and Reason-Annotated Dataset of Unnatural Speech","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2301.07087","title":"MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2306.00535","title":"The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2309.09652","title":"Speech Synthesis By Unrolling Diffusion Process using Neural Network Layers","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2311.16604","title":"LC4SV: A Denoising Framework Learning to Compensate for Unseen Speaker Verification Models","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2602.14785","title":"SA-SSL-MOS: Self-supervised Learning MOS Prediction with Spectral Augmentation for Generalized Multi-Rate Speech Assessment","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.15484","title":"Bottleneck Transformer-Based Approach for Improved Automatic STOI Score Prediction","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.16201","title":"Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlations","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2606.03241","title":"Benchmarking Speech-to-Speech Translation Models","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.10010","title":"DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.18645","title":"Augmenting Dysarthric Speech Severity Assessment with MOS Supervision","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.19951","title":"Investigating Human-Model Discrepancies in Speech Quality Assessment via Acoustic and Prosodic Perturbations","created":"2026-06-18","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":"2607.01965","title":"Towards a Phonology-Informed Evaluation of Multilingual TTS","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.08256","title":"Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.21176","title":"DAMOS: Learning Distortion-Aware Speech Quality Assessment through Explicit Distortion Localization","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.31035","title":"When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.14956","title":"CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Models","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.35054","title":"Perceptual Quality Loss or Loss of Perceptual Quality?","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}