paper-with-me

홈 › Papers

TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation

2025-08-27 · Shashi Kumar, Srikanth Madikeri, Esaú Villatoro-Tello, Sergio Burdisso, Pradeep Rangappa, Andrés Carofilis, Petr Motlicek, Karthik Pandia, Shankar Venkatesan, Kadri Hacioğlu, Andreas Stolcke arxiv

Token-based multitasking frameworks like TokenVerse require all training utterances to have labels for all tasks, hindering their ability to leverage partially annotated datasets and scale effectively. We propose TokenVerse++, which introduces learnable vectors in the acoustic embedding space of the XLSR-Transducer ASR model for dynamic task activation. This core mechanism enables training with utterances labeled for only a subset of tasks, a key advantage over TokenVerse. We demonstrate this by successfully integrating a dataset with partial labels, specifically for ASR and an additional task, language identification, improving overall performance. TokenVerse++ achieves results on par with or exceeding TokenVerse across multiple tasks, establishing it as a more practical multitask alternative without sacrificing ASR performance.

📄 PDF Abstract BibTeX arXiv:2508.19856

Code (0)

등록된 구현이 없습니다.

Tasks

Language Identification

Similar Papers 제목 키워드 기반

TokenVerse: Towards Unifying Speech and NLP Tasks via Transducer-based ASR

2024-07-05 · Shashi Kumar, Srikanth Madikeri, Juan Zuluaga-Gomez, Iuliia Thorbecke 외

In traditional conversational intelligence from speech, a cascaded pipeline is used, involving tasks such as voice activity detection, diarization, transcription, and subsequent processing with different NLP models for t…

Action DetectionActivity DetectionChange Detectionnamed-entity-recognition+4

TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space

2025-01-21 · Daniel Garibi, Shahar Yadin, Roni Paiss, Omer Tov 외

We present TokenVerse -- a method for multi-concept personalization, leveraging a pre-trained text-to-image diffusion model. Our framework can disentangle complex visual elements and attributes from as little as a single…

TransGP: Task-Conditioned Transformer-Guided Genetic Programming for Multitask Dynamic Flexible Job Shop Scheduling

2026-04-04 · Meng Xu, Jiao Liu, Hua Yu, Yew Soon Ong arxiv

Hyper-heuristics have become a popular approach for solving dynamic flexible job shop scheduling (DFJSS) problems. They use gradient-free optimization techniques like Genetic Programming (GP) to evolve non-differentiable…

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

2020-04-30 · ICML 2020 1 · Daniel Guo, Bernardo Avila Pires, Bilal Piot, Jean-bastien Grill 외

Learning a good representation is an essential component for deep reinforcement learning (RL). Representation learning is especially important in multitask and partially observable settings where building a representatio…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Multitask learning for instrument activation aware music source separation

2020-08-03 · Yun-Ning Hung, Alexander Lerch

Music source separation is a core task in music information retrieval which has seen a dramatic improvement in the past years. Nevertheless, most of the existing systems focus exclusively on the problem of source separat…

Information RetrievalMusic Information RetrievalMusic Source SeparationRetrieval