Copertina

The Cascade Equivalence Hypothesis: When Do Speech LLMs Behave Like ASR$\rightarrow$LLM Pipelines?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Billa, Jayadev
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence Audio and Speech Processing
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration
di: Billa, Jayadev
Pubblicazione: (2026)

Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM
di: Prakash, Jeena, et al.
Pubblicazione: (2025)

CTC-Assisted LLM-Based Contextual ASR
di: Yang, Guanrou, et al.
Pubblicazione: (2024)

Utterance-Level Methods for Identifying Reliable ASR-Output for Child Speech
di: Lathouwers, Gus, et al.
Pubblicazione: (2026)

Beyond Oversmoothing: Evaluating DDPM and MSE for Scalable Speech Synthesis in ASR
di: Minixhofer, Christoph, et al.
Pubblicazione: (2024)

When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation
di: Min, Anna, et al.
Pubblicazione: (2025)

Articulation-Informed ASR: Integrating Articulatory Features into ASR via Auxiliary Speech Inversion and Cross-Attention Fusion
di: Attia, Ahmed Adel, et al.
Pubblicazione: (2025)

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
di: Zhuo, Jianheng, et al.
Pubblicazione: (2025)

Streaming Speech-to-Text Translation with a SpeechLLM
di: Parcollet, Titouan, et al.
Pubblicazione: (2026)

Can Speech LLMs Think while Listening?
di: Shih, Yi-Jen, et al.
Pubblicazione: (2025)

Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones
di: Teleki, Maria, et al.
Pubblicazione: (2025)

Speech ReaLLM -- Real-time Streaming Speech Recognition with Multimodal LLMs by Teaching the Flow of Time
di: Seide, Frank, et al.
Pubblicazione: (2024)

Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models
di: Shakhadri, Syed Abdul Gaffar, et al.
Pubblicazione: (2025)

Closing the Gap Between Text and Speech Understanding in LLMs
di: Cuervo, Santiago, et al.
Pubblicazione: (2025)

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation
di: Srivastav, Vaibhav, et al.
Pubblicazione: (2025)

Advancing Speech Summarization in Multi-modal LLMs with Reinforcement Learning
di: Ling, Shaoshi, et al.
Pubblicazione: (2025)

Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMs
di: Satish, Shree Harsha Bokkahalli, et al.
Pubblicazione: (2025)

When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition
di: Moure, Pehuén, et al.
Pubblicazione: (2026)

What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
di: Fan, Xiaoran, et al.
Pubblicazione: (2025)

Enhancing ASR Performance in the Medical Domain for Dravidian Languages
di: Devarakonda, Sri Charan, et al.
Pubblicazione: (2026)

Exploring ASR-Based Wav2Vec2 for Automated Speech Disorder Assessment: Insights and Analysis
di: Nguyen, Tuan, et al.
Pubblicazione: (2024)

CMT-LLM: Contextual Multi-Talker ASR Utilizing Large Language Models
di: He, Jiajun, et al.
Pubblicazione: (2025)

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
di: Cao, Di, et al.
Pubblicazione: (2026)

LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR
di: Song, Zheshu, et al.
Pubblicazione: (2024)

TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition
di: Yang, Cheng-Yeh, et al.
Pubblicazione: (2026)

Toward Responsible ASR for African American English Speakers: A Scoping Review of Bias and Equity in Speech Technology
di: Cunningham, Jay L., et al.
Pubblicazione: (2025)

A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario
di: Song, Zheshu, et al.
Pubblicazione: (2024)

Speech-Based Cognitive Screening: A Systematic Evaluation of LLM Adaptation Strategies
di: Taherinezhad, Fatemeh, et al.
Pubblicazione: (2025)

LASER: An LLM-based ASR Scoring and Evaluation Rubric
di: Parulekar, Amruta, et al.
Pubblicazione: (2025)

An Embarrassingly Simple Approach for LLM with Strong ASR Capacity
di: Ma, Ziyang, et al.
Pubblicazione: (2024)

Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gap
di: Yang, Guanrou, et al.
Pubblicazione: (2024)

Fun-ASR Technical Report
di: An, Keyu, et al.
Pubblicazione: (2025)

EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting
di: Yang, Guanrou, et al.
Pubblicazione: (2025)

Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages
di: Fong, Seraphina, et al.
Pubblicazione: (2025)

A Unified Speech LLM for Diarization and Speech Recognition in Multilingual Conversations
di: Saengthong, Phurich, et al.
Pubblicazione: (2025)

Efficient Streaming LLM for Speech Recognition
di: Jia, Junteng, et al.
Pubblicazione: (2024)

Pronunciation-Lexicon Free Training for Phoneme-based Crosslingual ASR via Joint Stochastic Approximation
di: Yusuyin, Saierdaer, et al.
Pubblicazione: (2025)

Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition
di: Ma, Ziyang, et al.
Pubblicazione: (2023)

Zero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and Opportunities
di: Parikh, Aditya Kamlesh, et al.
Pubblicazione: (2026)

Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation
di: Wang, Qiongqiong, et al.
Pubblicazione: (2025)