{"total":41,"rows":[{"id":"2303.01037","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","created":"2023-03-02","cited_by_count":231,"area":null},{"id":"2303.03926","title":"Speak Foreign Languages with Your Own Voice: Cross-Lingual Neural Codec Language Modeling","created":"2023-03-07","cited_by_count":167,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2305.15255","title":"Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM","created":"2023-05-24","cited_by_count":94,"area":null},{"id":"2310.09424","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","created":"2023-10-13","cited_by_count":76,"area":null},{"id":"2408.17175","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","created":"2024-08-30","cited_by_count":72,"area":null},{"id":"2210.03730","title":"SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training","created":"2022-10-07","cited_by_count":40,"area":null},{"id":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37,"area":null},{"id":"2310.08715","title":"Toward Joint Language Modeling for Speech Units and Text","created":"2023-10-12","cited_by_count":28,"area":null},{"id":"2402.16915","title":"More Than Routing: Joint GPS and Route Modeling for Refine Trajectory Representation Learning","created":"2024-02-25","cited_by_count":20,"area":null},{"id":"2305.17547","title":"Translatotron 3: Speech to Speech Translation with Monolingual Data","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2312.09781","title":"GSQA: An End-to-End Model for Generative Spoken Question Answering","created":"2023-12-15","cited_by_count":9,"area":null},{"id":"2211.07321","title":"MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets","created":"2022-11-14","cited_by_count":8,"area":null},{"id":"2212.09553","title":"Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2410.15017","title":"DM-Codec: Distilling Multimodal Representations for Speech Tokenization","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2310.14278","title":"Conversational Speech Recognition by Learning Audio-textual Cross-modal Contextual Representation","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2311.07093","title":"A Comprehensive Study on the Effectiveness of ASR Representations for Noise-Robust Speech Emotion Recognition","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2406.05547","title":"Exploring the Benefits of Tokenization of Discrete Acoustic Units","created":"2024-06-08","cited_by_count":4,"area":null},{"id":"2406.14092","title":"Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2509.04605","title":"Spoken in Jest, Detected in Earnest: A Systematic Review of Sarcasm Recognition -- Multimodal Fusion, Challenges, and Future Prospects","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2210.16755","title":"token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text","created":"2022-10-30","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":"2411.07607","title":"CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR","created":"2024-11-12","cited_by_count":3,"area":null},{"id":"2406.09950","title":"An efficient text augmentation approach for contextualized Mandarin speech recognition","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2408.17432","title":"Text-to-Speech for Unseen Speakers via Low-Complexity Discrete Unit-Based Frame Selection","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2501.15090","title":"Speech Translation Refinement using Large Language Models","created":"2025-01-25","cited_by_count":2,"area":null},{"id":"2505.10599","title":"UDDETTS: Unifying Discrete and Dimensional Emotions for Controllable Emotional Text-to-Speech","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2506.14190","title":"AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2511.00256","title":"NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2306.01327","title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2307.12498","title":"Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2310.05919","title":"Few-Shot Spoken Language Understanding via Joint Speech-Text Models","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2405.01004","title":"Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2406.08380","title":"Towards Unsupervised Speech Recognition Without Pronunciation Models","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2410.05146","title":"CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2603.20042","title":"LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2606.14791","title":"From Physics to Representation: Audio Learning with Synthetic Pre-training via Procedural Generation","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2309.00174","title":"Typing on Any Surface: A Deep Learning-based Method for Real-Time Keystroke Detection in Augmented Reality","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2310.05374","title":"Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2410.03146","title":"Bridging the Gap between Text, Audio, Image, and Any Sequence: A Novel Approach using Gloss-based Annotation","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2609.11302","title":"Automatic Lyric Transcription for Greek Songs: Scaling and Task Composition Effects in Whisper Adaptation","created":"2026-09-10","cited_by_count":0,"area":null}],"next_cursor":null}