No article text was recorded for this version.
cross-attention feature fusion
Version 1 of 142 papers54 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings
- Blog: SA-SOT: Speaker-Aware Serialized Output Training for Multi-Talker ASR
- Blog: Multi-pass Training and Cross-information Fusion for Low-resource End-to-end Accented Speech Recognition
- Blog: Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture
- Blog: Monaural Multi-Talker Speech Recognition with Attention Mechanism and Gated Convolutional Networks
- Blog: Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM
- Blog: Improving Neural Diarization through Speaker Attribute Attractors and Local Dependency Modeling
- Blog: Enroll-Aware Attentive Statistics Pooling for Target Speaker Verification
- Blog: Joint speaker encoder and neural back-end model for fully end-to-end automatic speaker verification with multiple enrollment utterances
- Blog: Neural Speaker Extraction with Speaker-Speech Cross-Attention Network
- Blog: Binaural Selective Attention Model for Target Speaker Extraction
- Blog: An Exploration of Task-decoupling on Two-stage Neural Post Filter for Real-time Personalized Acoustic Echo Cancellation
- Blog: Speech Enhancement with Fullband-Subband Cross-Attention Network
- Blog: End-to-End Monaural Multi-speaker ASR System without Pretraining
- Blog: Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments
- Blog: Improving the Training Recipe for a Robust Conformer-based Hybrid Model
- Blog: Deeply Fused Speaker Embeddings for Text-Independent Speaker Verification
- Blog: DiEmo-TTS: Disentangled Emotion Representations via Self-Supervised Distillation for Cross-Speaker Emotion Transfer in Text-to-Speech
- Blog: EmoSpeechAuth: Emotion-Aware Speaker Verification
- Blog: Speaker Separation Using Speaker Inventories and Estimated Speech
- Blog: BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR
- Blog: Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction
- Blog: SEF-Net: Speaker Embedding Free Target Speaker Extraction Network
- Blog: Distinctive and Natural Speaker Anonymization via Singular Value Transformation-Assisted Matrix
- Blog: One-Shot Voice Conversion with Global Speaker Embeddings
- Blog: Attention-based conditioning methods using variable frame rate for style-robust speaker verification
- Blog: FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention
- Blog: Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor
- Blog: Multi-Level Attention Aggregation for Language-Agnostic Speaker Replication
- Blog: Attentive to Individual: A Multimodal Emotion Recognition Network with Personalized Attention Profile
- Blog: Late Audio-Visual Fusion for in-the-Wild Speaker Diarization
- Blog: CLN-VC: Text-Free Voice Conversion Based on Fine-Grained Style Control and Contrastive Learning with Negative Samples Augmentation
- Blog: Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of any Number of Speakers
- Blog: MIRNet: Learning Multiple Identities Representations in Overlapped Speech
- Blog: MFR-Net: Multi-faceted Responsive Listening Head Generation via Denoising Diffusion Model
- Blog: DAFMSVC: One-Shot Singing Voice Conversion with Dual Attention Mechanism and Flow Matching
- Blog: EAD-VC: Enhancing Speech Auto-Disentanglement for Voice Conversion with IFUB Estimator and Joint Text-Guided Consistent Learning
- Blog: End-to-end Anchored Speech Recognition
- Blog: Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion
- Blog: Improving Transformer-based End-to-End Speaker Diarization by Assigning Auxiliary Losses to Attention Heads
- Blog: Personalized Keyword Spotting through Multi-task Learning
- Blog: Personalized speech enhancement combining band-split RNN and speaker attentive module
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_cross_attention_feature_fusion_eae327c2,
title = {cross-attention feature fusion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-attention-feature-fusion/rdr_eae327c2902b4c6290972476baf96110},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_cross_attention_feature_fusion_eae327c2_v1,
title = {cross-attention feature fusion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/cross-attention-feature-fusion/rdr_eae327c2902b4c6290972476baf96110/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}