论文解读
Text-Dependent Speaker Verification (TdSV) Challenge 2024: Team Naive System Report
说话人验证 | 5.5/10
迁移学习
论文解读
Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition
语音识别 | 7.0/10
论文解读
WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data
语音识别 | 7.0/10
论文解读
A Semi-Supervised Framework for Speech Confidence Detection using Whisper
语音自信度检测 | 6.5/10
论文解读
jina-embeddings-v5-omni: Text-Geometry-Preserving Multimodal Embeddings via Frozen-Tower Composition
多模态检索 | 7.5/10
论文解读
Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker Diarization
语音识别 说话人日志 | 5.5/10
论文解读
CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
脑机接口 | 6.5/10
论文解读
Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation
音乐生成 | 7.5/10
论文解读
The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail
语音识别 | 8.5/10
论文解读
Spoken Language Identification with Pre-trained Models and Margin Loss
说话人识别 | 7.5/10
论文解读
Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?
音乐生成 | 7.0/10
论文解读
Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
音频分类 | 7.0/10
论文解读
From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings
音频分类 | 6.5/10
论文解读
MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation
语音增强 | 6.0/10
论文解读
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
模型比较 | 7.0/10
论文解读
SumRA: Parameter Efficient Fine-tuning with Singular Value Decomposition and Summed Orthogonal Basis
语音识别 | 7.5/10
论文解读
Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification
生物声学 | 7.0/10
论文解读
Predicting Upcoming Stuttering Events from Three-Second Audio: Stratified Evaluation Reveals Severity-Selective Precursors, and the Model Deploys Fully On-Device
语音生物标志物 | 7.0/10
论文解读
Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost
语音合成 | 8.0/10
论文解读
A Parameter-Efficient Multi-Scale Convolutional Adapter for Synthetic Speech Detection
A Parameter-Efficient Multi-Scale Convolutional Adapter for Synthetic Speech Detection