{"total":68,"rows":[{"id":"2409.06666","title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","created":"2024-09-10","cited_by_count":173,"area":null},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109,"area":null},{"id":"2408.02622","title":"Language Model Can Listen While Speaking","created":"2024-08-05","cited_by_count":63,"area":null},{"id":"2502.06490","title":"Recent Advances in Discrete Speech Tokens: A Review","created":"2025-02-10","cited_by_count":43,"area":null},{"id":"2407.21315","title":"Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances","created":"2024-07-31","cited_by_count":27,"area":null},{"id":"2411.06437","title":"CTC-Assisted LLM-Based Contextual ASR","created":"2024-11-10","cited_by_count":19,"area":null},{"id":"2411.03866","title":"Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forward","created":"2024-11-06","cited_by_count":17,"area":null},{"id":"2405.02132","title":"Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets","created":"2024-05-03","cited_by_count":13,"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":"2503.02769","title":"InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training","created":"2025-03-04","cited_by_count":11,"area":null},{"id":"2510.22603","title":"Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs","created":"2025-10-26","cited_by_count":11,"area":null},{"id":"2408.17431","title":"Advancing Multi-talker ASR Performance with Large Language Models","created":"2024-08-30","cited_by_count":10,"area":null},{"id":"2412.08237","title":"TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch","created":"2024-12-11","cited_by_count":10,"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":"2505.22251","title":"Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2408.16542","title":"SALSA: Speedy ASR-LLM Synchronous Aggregation","created":"2024-08-29","cited_by_count":8,"area":null},{"id":"2601.20900","title":"Text-only adaptation in LLM-based ASR through text denoising","created":"2026-01-28","cited_by_count":8,"area":null},{"id":"2506.05671","title":"Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2508.05149","title":"Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2505.21138","title":"Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2409.17044","title":"How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2506.08633","title":"Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2506.09448","title":"OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2507.19308","title":"The Eloquence team submission for task 1 of MLC-SLM challenge","created":"2025-07-25","cited_by_count":4,"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":"2412.15995","title":"Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2506.04711","title":"LLM-based phoneme-to-grapheme for phoneme-based speech recognition","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2410.15029","title":"Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-Attention","created":"2024-10-19","cited_by_count":2,"area":null},{"id":"2505.16212","title":"Large Language Models based ASR Error Correction for Child Conversations","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2509.07526","title":"Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2601.20898","title":"Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2603.27981","title":"On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2406.14701","title":"Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2409.16005","title":"Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2412.00721","title":"A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2502.09284","title":"SparQLe: Speech Queries to Text Translation Through LLMs","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2506.11064","title":"PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2506.12059","title":"CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2506.12537","title":"What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2506.13596","title":"Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2509.19902","title":"WEST: LLM based Speech Toolkit for Speech Understanding, Generation, and Interaction","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2604.22817","title":"In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word Level Timestamp Predictions","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2607.22100","title":"MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2405.18669","title":"Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2406.05839","title":"MaLa-ASR: Multimedia-Assisted LLM-Based ASR","created":"2024-06-09","cited_by_count":0,"area":null},{"id":"2502.16142","title":"Understanding Zero-shot Rare Word Recognition Improvements Through LLM Integration","created":"2025-02-22","cited_by_count":0,"area":null},{"id":"2505.14505","title":"ModRWKV: Transformer Multimodality in Linear Time","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2506.13339","title":"NTU Speechlab LLM-Based Multilingual ASR System for Interspeech MLC-SLM Challenge 2025","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2506.13396","title":"Bi-directional Context-Enhanced Speech Large Language Models for Multilingual Conversational ASR","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2508.08095","title":"Dual Information Speech Language Models for Emotional Conversations","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2508.11771","title":"Investigating Transcription Normalization in the Faetar ASR Benchmark","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2508.14916","title":"Transsion Multilingual Speech Recognition System for MLC-SLM 2025 Challenge","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2508.19856","title":"TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.15667","title":"VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2511.09232","title":"POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2603.05121","title":"Measuring the Redundancy of Decoder Layers in SpeechLLMs","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.06487","title":"Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.14766","title":"Streaming Speech-to-Text Translation with a SpeechLLM","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.25444","title":"Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.02763","title":"LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.11587","title":"Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.05871","title":"Where Does the Sound Go? Tracing Acoustic Information Loss in Audio-Conditioned LLMs","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.11762","title":"Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.17981","title":"Encoder Awakening via Adapters: Effective Domain-Adaptive Fine-tuning of Speech-LLMs","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20081","title":"Reading Emotions in the Token Space: Discriminative Adaptation of SpeechLLMs for Emotion Recognition","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.08085","title":"DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08994","title":"Phoneme-Guided Initialization for LLM-based Speech Recognition","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.11159","title":"Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}