Cover Image

Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Hojun, Hong, Eunsoo, Hyung, Ziwon, Lim, Sungjun, Lee, Seungjin, Cho, Keunseok
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Sound Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Evaluating Automatic Speech Recognition Systems for Korean Meteorological Experts
by: Park, ChaeHun, et al.
Published: (2024)

DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech
by: Cho, Deok-Hyeon, et al.
Published: (2025)

CTC-aligned Audio-Text Embedding for Streaming Open-vocabulary Keyword Spotting
by: Jin, Sichen, et al.
Published: (2024)

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
by: Kim, Jaehyeon, et al.
Published: (2024)

Comparison of Speech Tasks in Human Expert and Machine Detection of Parkinson's Disease
by: Plantinga, Peter, et al.
Published: (2025)

EmoSphere++: Emotion-Controllable Zero-Shot Text-to-Speech via Emotion-Adaptive Spherical Vector
by: Cho, Deok-Hyeon, et al.
Published: (2024)

CAMEL: Cross-Attention Enhanced Mixture-of-Experts and Language Bias for Code-Switching Speech Recognition
by: Wang, He, et al.
Published: (2024)

Style Mixture of Experts for Expressive Text-To-Speech Synthesis
by: Jawaid, Ahad, et al.
Published: (2024)

Evaluating Self-Supervised Speech Models via Text-Based LLMS
by: Maekaku, Takashi, et al.
Published: (2025)

NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers
by: Park, Nohil, et al.
Published: (2024)

Beyond Speaker Identity: Text Guided Target Speech Extraction
by: Huo, Mingyue, et al.
Published: (2025)

EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech
by: Cho, Deok-Hyeon, et al.
Published: (2024)

GigaAM: Efficient Self-Supervised Learner for Speech Recognition
by: Kutsakov, Aleksandr, et al.
Published: (2025)

Leveraging Mixture of Experts for Improved Speech Deepfake Detection
by: Negroni, Viola, et al.
Published: (2024)

Sparsely Shared LoRA on Whisper for Child Speech Recognition
by: Liu, Wei, et al.
Published: (2023)

Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition
by: Mu, Bingshen, et al.
Published: (2025)

VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature
by: Du, Chenpeng, et al.
Published: (2022)

MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts
by: Xue, Heyang, et al.
Published: (2025)

Enhancing Code-Switching Speech Recognition with LID-Based Collaborative Mixture of Experts Model
by: Huang, Hukai, et al.
Published: (2024)

Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks
by: Du, Yichao, et al.
Published: (2024)

SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models
by: Yang, Dongchao, et al.
Published: (2024)

Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning
by: Changin, Choi, et al.
Published: (2024)

Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation
by: Shin, Ui-Hyeop, et al.
Published: (2026)

Active Learning of Non-semantic Speech Tasks with Pretrained Models
by: Lee, Harlin, et al.
Published: (2022)

Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion
by: Li, Ruiqi, et al.
Published: (2024)

MATS: An Audio Language Model under Text-only Supervision
by: Wang, Wen, et al.
Published: (2025)

VoiceGuider: Enhancing Out-of-Domain Performance in Parameter-Efficient Speaker-Adaptive Text-to-Speech via Autoguidance
by: Yeom, Jiheum, et al.
Published: (2024)

Efficient Extraction of Noise-Robust Discrete Units from Self-Supervised Speech Models
by: Poncelet, Jakob, et al.
Published: (2024)

Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition
by: Shin, Ui-Hyeop, et al.
Published: (2023)

EELE: Exploring Efficient and Extensible LoRA Integration in Emotional Text-to-Speech
by: Qi, Xin, et al.
Published: (2024)

MultiVerse: Efficient and Expressive Zero-Shot Multi-Task Text-to-Speech
by: Bak, Taejun, et al.
Published: (2024)

Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations
by: Li, Jialu, et al.
Published: (2024)

VoiceTailor: Lightweight Plug-In Adapter for Diffusion-Based Personalized Text-to-Speech
by: Kim, Heeseung, et al.
Published: (2024)

Erasing Your Voice Before It's Heard: Training-free Speaker Unlearning for Zero-shot Text-to-Speech
by: Lee, Myungjin, et al.
Published: (2026)

ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer
by: Liu, Huadai, et al.
Published: (2023)

Pseudo Labels-based Neural Speech Enhancement for the AVSR Task in the MISP-Meeting Challenge
by: Luo, Longjie, et al.
Published: (2025)

Instance-Specific Test-Time Training for Speech Editing in the Wild
by: Kim, Taewoo, et al.
Published: (2025)

Naturalness-Aware Curriculum Learning with Dynamic Temperature for Speech Deepfake Detection
by: Kim, Taewoo, et al.
Published: (2025)

In This Environment, As That Speaker: A Text-Driven Framework for Multi-Attribute Speech Conversion
by: Jin, Jiawei, et al.
Published: (2025)

Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM
by: Zhang, Fengrun, et al.
Published: (2024)