paper-with-me

Papers

Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion

2025-06-02 · Kumud Tripathi, Chowdam Venkata Kumar, Pankaj Wasnik

Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper. We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention (CA). Experimental results reveal that simple fusion techniques, particularly addition, outperform CA in both accuracy and efficiency. Fusion-based models consistently surpass single-feature models, highlighting the complementary nature of MFCCs and PTM features. Notably, our best-performing fusion model exceeds the state-of-the-art Pyannote across multiple datasets, achieving an absolute average improvement of 2.04%. These results confirm that simple feature fusion enhances VAD robustness while maintaining computational efficiency.

📄 PDF Abstract BibTeX arXiv:2506.01365

Code (0)

등록된 구현이 없습니다.

Tasks

Action DetectionActivity DetectionComputational Efficiency

Similar Papers 제목 키워드 기반

MLNET: An Adaptive Multiple Receptive-field Attention Neural Network for Voice Activity Detection

2020-08-13 · Zhenpeng Zheng, Jianzong Wang, Ning Cheng, Jian Luo 외

Voice activity detection (VAD) makes a distinction between speech and non-speech and its performance is of crucial importance for speech based services. Recently, deep neural network (DNN)-based VADs have achieved better…

Action DetectionActivity Detection

VSANet: Real-time Speech Enhancement Based on Voice Activity Detection and Causal Spatial Attention

2023-10-11 · Yuewei Zhang, Huanbin Zou, Jie Zhu

The deep learning-based speech enhancement (SE) methods always take the clean speech's waveform or time-frequency spectrum feature as the learning target, and train the deep neural network (DNN) by reducing the error los…

Action DetectionActivity DetectionMulti-Task LearningSpeech Enhancement

Window Size Versus Accuracy Experiments in Voice Activity Detectors

2026-01-24 · Max McKinnon, Samir Khaki, Chandan KA Reddy, William Huang arxiv

Voice activity detection (VAD) plays a vital role in enabling applications such as speech recognition. We analyze the impact of window size on the accuracy of three VAD algorithms: Silero, WebRTC, and Root Mean Square (R…

Speech RecognitionActivity Detection

Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection

2024-01-10 · Koji Inoue, Bing'er Jiang, Erik Ekstedt, Tatsuya Kawahara 외

A demonstration of a real-time and continuous turn-taking prediction system is presented. The system is based on a voice activity projection (VAP) model, which directly maps dialogue stereo audio to future voice activiti…

CPU

Real-Time Voicemail Detection in Telephony Audio Using Temporal Speech Activity Features

2026-04-02 · Kumar Saurav arxiv

Outbound AI calling systems must distinguish voicemail greetings from live human answers in real time to avoid wasted agent interactions and dropped calls. We present a lightweight approach that extracts 15 temporal feat…

Feature Importance