Image de couverture de livre

Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Jingxiang, Kim, Minseok, Leem, Seong-Gyun, Huang, Yin, Rungta, Rashi, Ouyang, Zhicheng, Wu, Haibin, Appini, Surya Teja, Bansal, Ankur, Bai, Yang, Liu, Yue, Metze, Florian, Aly, Ahmed A, Kumar, Anuj, Rastrow, Ariya, Lin, Zhaojiang
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning
par: Ouyang, Zhicheng, et autres
Publié: (2026)

Streaming Speech-to-Confusion Network Speech Recognition
par: Filimonov, Denis, et autres
Publié: (2023)

Speech Recognition Rescoring with Large Speech-Text Foundation Models
par: Shivakumar, Prashanth Gurunath, et autres
Publié: (2024)

Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
par: Arora, Siddhant, et autres
Publié: (2025)

Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition
par: Chan, David M., et autres
Publié: (2024)

Multi-Modal Retrieval For Large Language Model Based Speech Recognition
par: Kolehmainen, Jari, et autres
Publié: (2024)

Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environment
par: Leem, Seong-Gyun, et autres
Publié: (2024)

WearVox: An Egocentric Multichannel Voice Assistant Benchmark for Wearables
par: Lin, Zhaojiang, et autres
Publié: (2025)

CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
par: Lu, Yen-Ju, et autres
Publié: (2024)

ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction
par: Yang, Shu-wen, et autres
Publié: (2025)

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition
par: Xie, Jiamin, et autres
Publié: (2025)

Versatile audio-visual learning for emotion recognition
par: Goncalves, Lucas, et autres
Publié: (2023)

suryatejabatchu08/Parkinsonian-Gait-Assessment: PGSI: Pose-Derived Parkinsonian Gait Severity Index — Initial Release
par: Surya Teja
Publié: (2026)

Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning
par: Cayir, Derin, et autres
Publié: (2025)

An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems
par: Tulsiani, Hitesh, et autres
Publié: (2024)

Towards Machine Unlearning for Paralinguistic Speech Processing
par: Phukan, Orchid Chetia, et autres
Publié: (2025)

PROCTER: PROnunciation-aware ConTextual adaptER for personalized speech recognition in neural transducers
par: Pandey, Rahul, et autres
Publié: (2023)

Identity Control Plane: The Unifying Layer for Zero Trust Infrastructure
par: Avirneni, Surya Teja
Publié: (2025)

Establishing Workload Identity for Zero Trust CI/CD: From Secrets to SPIFFE-Based Authentication
par: Avirneni, Surya Teja
Publié: (2025)

Intent-Aware Authorization for Zero Trust CI/CD
par: Avirneni, Surya Teja
Publié: (2025)

Decoupling Identity from Access: Credential Broker Patterns for Secure CI/CD
par: Avirneni, Surya Teja
Publié: (2025)

S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models
par: Jiang, Feng, et autres
Publié: (2025)

Are Paralinguistic Representations all that is needed for Speech Emotion Recognition?
par: Phukan, Orchid Chetia, et autres
Publié: (2024)

Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks
par: Buitrago, Pol, et autres
Publié: (2026)

Auditory Environments to Physical Environments
par: Ivaana Rungta
Publié: (2026)

Two-pass Endpoint Detection for Speech Recognition
par: Raju, Anirudh, et autres
Publié: (2024)

SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding
par: Bai, Bingsong, et autres
Publié: (2025)

SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation
par: Liu, Ruohan, et autres
Publié: (2026)

Incorporating Contextual Paralinguistic Understanding in Large Speech-Language Models
par: Wang, Qiongqiong, et autres
Publié: (2025)

Comparative Analysis of Data Warehousing Solutions: AWS Redshift vs. Snowflake vs. Google BigQuery
par: Naga Surya Teja Thallam
Publié: (2020)

Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue
par: Lin, Guan-Ting, et autres
Publié: (2023)

Mind, Meaning and Architecture
par: Ivaana Rungta, Ivaana
Publié: (2026)

Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech
par: Kang, Wonjune, et autres
Publié: (2024)

Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
par: Kim, Heeseung, et autres
Publié: (2024)

Beyond the Labels: Unveiling Text-Dependency in Paralinguistic Speech Recognition Datasets
par: Pešán, Jan, et autres
Publié: (2024)

UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations
par: Haq, Attia Nafees ul, et autres
Publié: (2026)

An Introduction to Silent Paralinguistics
par: Ren, Zhao, et autres
Publié: (2025)

Efficient Algorithms for Partitioning Circulant Graphs with Optimal Spectral Approximation
par: Gavva, Surya Teja, et autres
Publié: (2025)

NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations
par: Liao, Huan, et autres
Publié: (2025)

Source Tracing of Synthetic Speech Systems Through Paralinguistic Pre-Trained Representations
par: Girish, et autres
Publié: (2025)