{"total":71,"rows":[{"id":"2211.03929","title":"Comparative layer-wise analysis of self-supervised speech models","created":"2022-11-08","cited_by_count":158,"area":null},{"id":"2503.04721","title":"Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities","created":"2025-03-06","cited_by_count":100,"area":null},{"id":"2305.10615","title":"ML-SUPERB: Multilingual Speech Universal PERformance Benchmark","created":"2023-05-18","cited_by_count":71,"area":null},{"id":"2301.13126","title":"LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain","created":"2023-01-30","cited_by_count":68,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2402.12786","title":"Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations","created":"2024-02-20","cited_by_count":45,"area":null},{"id":"2210.07185","title":"On the Utility of Self-supervised Models for Prosody-related Tasks","created":"2022-10-13","cited_by_count":42,"area":null},{"id":"2208.11761","title":"IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages","created":"2022-08-24","cited_by_count":40,"area":null},{"id":"2404.09385","title":"A Large-Scale Evaluation of Speech Foundation Models","created":"2024-04-15","cited_by_count":40,"area":null},{"id":"2210.15759","title":"Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge","created":"2022-10-27","cited_by_count":34,"area":null},{"id":"2210.00705","title":"SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model","created":"2022-10-03","cited_by_count":29,"area":null},{"id":"2306.00452","title":"Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?","created":"2023-06-01","cited_by_count":28,"area":null},{"id":"2210.08634","title":"SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning","created":"2022-10-16","cited_by_count":26,"area":null},{"id":"2305.11072","title":"Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering","created":"2023-05-18","cited_by_count":22,"area":null},{"id":"2306.02207","title":"SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts","created":"2023-06-03","cited_by_count":21,"area":null},{"id":"2203.16773","title":"SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks","created":"2022-03-31","cited_by_count":19,"area":null},{"id":"2309.10787","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","created":"2023-09-19","cited_by_count":19,"area":null},{"id":"2309.05472","title":"LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech","created":"2023-09-11","cited_by_count":18,"area":null},{"id":"2506.05140","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","created":"2025-06-05","cited_by_count":18,"area":null},{"id":"2308.14456","title":"Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads","created":"2023-08-28","cited_by_count":17,"area":null},{"id":"2504.07053","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","created":"2025-04-09","cited_by_count":16,"area":null},{"id":"2408.13040","title":"SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks","created":"2024-08-23","cited_by_count":12,"area":null},{"id":"2204.02470","title":"Combining Spectral and Self-Supervised Features for Low Resource Speech Recognition and Translation","created":"2022-04-05","cited_by_count":11,"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":"2306.08374","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","created":"2023-06-14","cited_by_count":9,"area":null},{"id":"2309.07707","title":"CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2406.10083","title":"On the Evaluation of Speech Foundation Models for Spoken Language Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2410.24177","title":"DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2503.16956","title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech","created":"2025-03-21","cited_by_count":9,"area":null},{"id":"2305.19011","title":"MiniSUPERB: Lightweight Benchmark for Self-supervised Speech Models","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2401.14664","title":"UNIT-DSR: Dysarthric Speech Reconstruction System Using Speech Unit Normalization","created":"2024-01-26","cited_by_count":8,"area":null},{"id":"2303.11131","title":"Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2311.09117","title":"R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2401.02839","title":"Pheme: Efficient and Conversational Speech Generation","created":"2024-01-05","cited_by_count":6,"area":null},{"id":"2211.05172","title":"Speech separation with large-scale self-supervised learning","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2406.12209","title":"Interface Design for Self-Supervised Speech Models","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2409.05910","title":"Property Neurons in Self-Supervised Speech Transformers","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2409.16295","title":"Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2503.00733","title":"UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2211.00586","title":"T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2412.11538","title":"MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2505.06660","title":"TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models","created":"2025-05-10","cited_by_count":4,"area":null},{"id":"2509.07139","title":"The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2211.03025","title":"Bridging Speech and Textual Pre-trained Models with Unsupervised ASR","created":"2022-11-06","cited_by_count":3,"area":null},{"id":"2211.08402","title":"Introducing Semantics into Speech Encoders","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2306.15464","title":"Large-scale unsupervised audio pre-training for video-to-speech synthesis","created":"2023-06-27","cited_by_count":3,"area":null},{"id":"2407.21066","title":"ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks","created":"2024-07-28","cited_by_count":3,"area":null},{"id":"2501.06562","title":"Discrete Speech Unit Extraction via Independent Component Analysis","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2210.13030","title":"Self-supervised Rewiring of Pre-trained Speech Encoders: Towards Faster Fine-tuning with Less Labels in Speech Processing","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2211.02332","title":"Once-for-All Sequence Compression for Self-Supervised Speech Models","created":"2022-11-04","cited_by_count":2,"area":null},{"id":"2310.10922","title":"Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2410.11243","title":"Investigation of Speaker Representation for Target-Speaker Speech Processing","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2502.12672","title":"Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.00071","title":"I see what you mean: Co-Speech Gestures for Reference Resolution in Multimodal Dialogue","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2407.03734","title":"Improving Self-supervised Pre-training using Accent-Specific Codebooks","created":"2024-07-04","cited_by_count":1,"area":null},{"id":"2408.13119","title":"Coarse-to-fine Alignment Makes Better Speech-image Retrieval","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2411.03085","title":"Speech Separation with Pretrained Frontend to Minimize Domain Mismatch","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2601.06329","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","created":"2026-01-09","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":"2605.10494","title":"Multi-layer attentive probing improves transfer of audio representations for bioacoustics","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2304.04618","title":"Enhancing Speech-to-Speech Translation with Multiple TTS Targets","created":"2023-04-10","cited_by_count":0,"area":null},{"id":"2306.00481","title":"Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations","created":"2023-06-01","cited_by_count":0,"area":null},{"id":"2307.12231","title":"Exploring the Integration of Speech Separation and Recognition with Self-Supervised Learning Representation","created":"2023-07-23","cited_by_count":0,"area":null},{"id":"2308.01018","title":"SALTTS: Leveraging Self-Supervised Speech Representations for improved Text-to-Speech Synthesis","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2310.03975","title":"HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2504.02302","title":"Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2508.20983","title":"Multilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge System","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2603.01482","title":"A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2606.30356","title":"OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2610.17619","title":"When Does an ASR Error Matter? Task-Role Diagnostics for Tool-Using Voice Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}