Imagen de Portada

From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ambilduke, Kshitij, Peters, Ben, Sannigrahi, Sonal, Keshwani, Anil, Lam, Tsz Kin, Martins, Bruno, Martins, André F. T., Boito, Marcely Zanon
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Instituto de Telecomunicações at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning
por: Attanasio, Giuseppe, et al.
Publicado: (2025)

SpeechMapper: Speech-to-text Embedding Projector for LLMs
por: Mohapatra, Biswesh, et al.
Publicado: (2026)

Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts
por: Ferraz, Thomas Palmeira, et al.
Publicado: (2023)

Compact Speech Translation Models via Discrete Speech Units Pretraining
por: Lam, Tsz Kin, et al.
Publicado: (2024)

NAVER LABS Europe Submission to the Instruction-following Track
por: Lee, Beomseok, et al.
Publicado: (2025)

mHuBERT-147: A Compact Multilingual HuBERT Model
por: Boito, Marcely Zanon, et al.
Publicado: (2024)

Did Translation Models Get More Robust Without Anyone Even Noticing?
por: Peters, Ben, et al.
Publicado: (2024)

Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases
por: Zhou, Giulio, et al.
Publicado: (2024)

Adding Chocolate to Mint: Mitigating Metric Interference in Machine Translation
por: Pombal, José, et al.
Publicado: (2025)

Chapter 32 The Role of Inclusion, Diversity, Equity, and Access (IDEA) in Agricultural and Biological Engineering
por: Keshwani, Deepak, et al.
Publicado: (2025)

TOWER OF BABEL
Publicado: (2006)

Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison
por: Lam, Tsz Kin, et al.
Publicado: (2025)

StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario
por: Boito, Marcely Zanon, et al.
Publicado: (2026)

Synthetic Query Generation using Large Language Models for Virtual Assistants
por: Sannigrahi, Sonal, et al.
Publicado: (2024)

Enhancing Context Through Contrast
por: Ambilduke, Kshitij, et al.
Publicado: (2024)

Different Speech Translation Models Encode and Translate Speaker Gender Differently
por: Fucci, Dennis, et al.
Publicado: (2025)

Analyzing Context Contributions in LLM-based Machine Translation
por: Zaranis, Emmanouil, et al.
Publicado: (2024)

TowerVision: Understanding and Improving Multilinguality in Vision-Language Models
por: Viveiros, André G., et al.
Publicado: (2025)

Asociación entre adopción y suicidio en adolescentes
por: Marcely Navarro-Gómez
Publicado: (2019)

Innovation Diffusion Among Case‐Based Decision‐Makers
por: Benson Tsz Kin Leung
Publicado: (2025)

The Prosody of Emojis
por: Zhou, Giulio, et al.
Publicado: (2025)

SPIRE: Structure-Preserving Interpretable Retrieval of Evidence
por: Rainey, Mike, et al.
Publicado: (2026)

SPIRE: Semantic Prompt-Driven Image Restoration
por: Qi, Chenyang, et al.
Publicado: (2023)

Evapotranspiration and precipitation at station TOWER on Samoylov Island
por: Helbig, Manuel, et al.
Publicado: (2013)

SEGMENTED WIND TURBINE TOWER CONNECTIONS: A STATE‐OF‐THE‐ART REVIEW, CLASSIFICATION, AND CASE STUDY OF A NOVEL MODULAR TOWER
por: J. M. Tekantappeh, et al.
Publicado: (2026)

TOWER: Tree Organized Weighting for Evaluating Complex Instructions
por: Ziems, Noah, et al.
Publicado: (2024)

SPIRE: Conditional Personalization for Federated Diffusion Generative Models
por: Ozkara, Kaan, et al.
Publicado: (2025)

PROYECTO DE CONSERVACIÓN DE LA WHITE TOWER
por: María Emilia Villagra Huijse
Publicado: (2010)

Ocular misalignment and unmet eye care needs among students with special education needs in Hong Kong
por: Kin Hei Lau, et al.
Publicado: (2026)

Pitfalls and Outlooks in Using COMET
por: Zouhar, Vilém, et al.
Publicado: (2024)

Attempt Towards Stress Transfer in Speech-to-Speech Machine Translation
por: Akarsh, Sai, et al.
Publicado: (2024)

Emergent Multisublattice Dynamics in Ferrimagnetic Dy 3 Fe 5 O 12
por: Jhuma Sannigrahi, et al.
Publicado: (2025)

Enhanced Network Traffic Classification Using Bayesian‐Optimized Logistic Regression and Random Forest Algorithm
por: Manisankar Sannigrahi, et al.
Publicado: (2025)

SPIRE HeRS/HeLMS Combined SHIM Maps
por: Zemcov, Michael, et al.
Publicado: (2024)

Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction
por: Fonseca, Rui, et al.
Publicado: (2025)

Reincidencia delictiva y la dinámica de hurto a equipos móviles en la localidad Puente Aranda, Bogotá, Colombia
por: Teniente Andrea Marcely Saavedra Ayala
Publicado: (2016)

Simply typed convertibility is TOWER-complete even for safe lambda-terms
por: Nguyên, Lê Thành Dũng
Publicado: (2023)

STRUCTURAL BEHAVIOUR OF A BOLTED SECTION AT THE KARLA TOWER GLASS BOX
por: Eliana Inca‐Cabrera, et al.
Publicado: (2026)

SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation
por: Zhou, Zihan, et al.
Publicado: (2024)

Estado e burguesia no capitalismo neoliberal
por: Armando Boito
Publicado: (2007)