Cover Image

Optimizing Speech Multi-View Feature Fusion through Conditional Computation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shan, Weiqiao, Zhang, Yuhao, Han, Yuchen, Li, Bei, Zhao, Xiaofeng, Li, Yuang, Zhang, Min, Yang, Hao, Xiao, Tong, Zhu, Jingbo
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Artificial Intelligence Computation and Language Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders
by: Shan, Weiqiao, et al.
Published: (2025)

Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
by: Zhang, Yuhao, et al.
Published: (2025)

DrawSpeech: Expressive Speech Synthesis Using Prosodic Sketches as Control Conditions
by: Chen, Weidong, et al.
Published: (2025)

Enhancing Intelligibility for Generative Target Speech Extraction via Joint Optimization with Target Speaker ASR
by: Ma, Hao, et al.
Published: (2025)

Large Language Model Should Understand Pinyin for Chinese ASR Error Correction
by: Li, Yuang, et al.
Published: (2024)

DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions
by: Niu, Shu-Tong, et al.
Published: (2024)

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation
by: Wu, Yusong, et al.
Published: (2022)

Emotion Recognition in Multi-Speaker Conversations through Speaker Identification, Knowledge Distillation, and Hierarchical Fusion
by: Li, Xiao, et al.
Published: (2025)

Attention-Based Beamformer For Multi-Channel Speech Enhancement
by: Bai, Jinglin, et al.
Published: (2024)

FleSpeech: Flexibly Controllable Speech Generation with Various Prompts
by: Li, Hanzhao, et al.
Published: (2025)

Speech Enhancement with Overlapped-Frame Information Fusion and Causal Self-Attention
by: Zhang, Yuewei, et al.
Published: (2025)

Improving Design of Input Condition Invariant Speech Enhancement
by: Zhang, Wangyou, et al.
Published: (2024)

Two Views, One Truth: Spectral and Self-Supervised Features Fusion for Robust Speech Deepfake Detection
by: Kheir, Yassine El, et al.
Published: (2025)

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM
by: Yu, Jiawei, et al.
Published: (2024)

StyleFusion TTS: Multimodal Style-control and Enhanced Feature Fusion for Zero-shot Text-to-speech Synthesis
by: Chen, Zhiyong, et al.
Published: (2024)

Comprehend and Talk: Text to Speech Synthesis via Dual Language Modeling
by: Cao, Junjie, et al.
Published: (2025)

Neural Vocoders as Speech Enhancers
by: Li, Andong, et al.
Published: (2025)

Cross-Domain Audio Deepfake Detection: Dataset and Analysis
by: Li, Yuang, et al.
Published: (2024)

EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization
by: Wang, Jianzong, et al.
Published: (2024)

CONTUNER: Singing Voice Beautifying with Pitch and Expressiveness Condition
by: Wang, Jianzong, et al.
Published: (2024)

Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy
by: Xue, Ke, et al.
Published: (2026)

Noise-Aware Speech Separation with Contrastive Learning
by: Zhang, Zizheng, et al.
Published: (2023)

Mamba in Speech: Towards an Alternative to Self-Attention
by: Zhang, Xiangyu, et al.
Published: (2024)

Listen through the Sound: Generative Speech Restoration Leveraging Acoustic Context Representation
by: Chung, Soo-Whan, et al.
Published: (2025)

Bridging Speech Emotion Recognition and Personality: Dataset and Temporal Interaction Condition Network
by: Gao, Yuan, et al.
Published: (2025)

Muyan-TTS: A Trainable Text-to-Speech Model Optimized for Podcast Scenarios with a $50K Budget
by: Li, Xin, et al.
Published: (2025)

STSM-FiLM: A FiLM-Conditioned Neural Architecture for Time-Scale Modification of Speech
by: Wisnu, Dyah A. M. G., et al.
Published: (2025)

Combining Deterministic Enhanced Conditions with Dual-Streaming Encoding for Diffusion-Based Speech Enhancement
by: Shi, Hao, et al.
Published: (2025)

Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation
by: Zhu, Qiushi, et al.
Published: (2024)

Joint Speaker Features Learning for Audio-visual Multichannel Speech Separation and Recognition
by: Li, Guinan, et al.
Published: (2024)

Conditional Latent Diffusion-Based Speech Enhancement Via Dual Context Learning
by: Zhao, Shengkui, et al.
Published: (2025)

Learning Expressive Disentangled Speech Representations with Soft Speech Units and Adversarial Style Augmentation
by: Deng, Yimin, et al.
Published: (2024)

Scale This, Not That: Investigating Key Dataset Attributes for Efficient Speech Enhancement Scaling
by: Zhang, Leying, et al.
Published: (2024)

MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction
by: Wang, Jianjin, et al.
Published: (2025)

Feature Importance across Domains for Improving Non-Intrusive Speech Intelligibility Prediction in Hearing Aids
by: Zezario, Ryandhimas E., et al.
Published: (2025)

Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization
by: Wan, Genshun, et al.
Published: (2026)

LL-SDR: Low-Latency Speech enhancement through Discrete Representations
by: Li, Jingyi, et al.
Published: (2026)

Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization
by: Hu, Yuchen, et al.
Published: (2024)

SICRN: Advancing Speech Enhancement through State Space Model and Inplace Convolution Techniques
by: Zhao, Changjiang, et al.
Published: (2024)

Rare Word Recognition and Translation Without Fine-Tuning via Task Vector in Speech Models
by: Jing, Ruihao, et al.
Published: (2025)