Show HN: RealtimeVAD – trading false positives for 110ms earlier end-of-speech
来源: Show HN ·
Hey guys. I recently watched the latency reports for my local voice assistant, which show a waveform plus silero probability for voice activity. I noticed silero lags visibly on the speech off signal. There had to be a method to get this signal closer to what I felt is optimal. My idea was to use a 10 ms energy detector with a threshold that adapts to environment or room noise. Which worked amazingly well. It created more false positives but in my speculative generation pipeline that would not matter. If it's wrong and the user continues speaking I can abort the pipeline fast. I benchmarked my
常见问题
什么是 Show HN: RealtimeVAD – trading false positives for 110ms earlier end-of-speech？
Show HN: RealtimeVAD – trading false positives for 110ms earlier end-of-speech is a 工具 discovery curated from Show HN. Hey guys. I recently watched the latency reports for my local voice assistant, which show a waveform plus silero probability for voice activity. I noticed silero lags visibly on…
如何访问或体验此内容？
You can experience this content directly on its original host (Show HN) by clicking the "Open Original" button.
此内容来源于哪里？
Curated from Show HN by the OnSuggest team to surface the most interesting and serendipitous content on the web.
相关发现
所有 开发者工具 发现 →Show HN: System requirements checking website for gamers along with optimization
I am building a system requirements checking website where gamers can check games will work or not based on their system specs Comments URL: https://news.ycombinator.com/item?id=50474089 Points: 1 # Comments: 0
Show HN: Cerulion – ROS 2-compatible robotics runtime with multi-process replay
Hi HN, I'm Lakshay. Raveen and I built Cerulion, an open-source Rust robotics runtime that deterministically replays recorded multi-process runs against new code and runs existing ROS 2 nodes unmodified. Repo: https://github.com/cerulion-inc/cerulion During my MIT PhD in off-road autonomy, a robot with two lidars and six cameras had too much latency between ROS processes. ROS 2's loaned messages need POD data, which rules out the standard sensor types like Image and PointCloud2. We ended up using a single process, which is very brittle. And when it broke, I couldn't reproduce the heisenbug rel
Show HN: Source – The attribution data layer for agents to drive pipeline
Attribution data your agents can query over MCP to drive pipeline: multi-touch and view-through conversions, outbound campaigns, and the organic searches that convert.
Show HN: Telltale Bot, detecting agentic web traffic
Telltale Bot tells website owners whether a visit comes from a person, from an AI agent acting for a person, or from a bot. It identifies; it never blocks.
Show HN: Kiln – A WebGPU alternative to transformers.js, 2.2× faster (median)
WebGPU-native LLM inference for the browser. Contribute to erdemozkan/kiln development by creating an account on GitHub.
Show HN: Buildout, Harmonies-based game to build AI Lab
Build your AI infrastructure network. Draft components, connect fiber routes, and deploy models in this strategy game for one to four players.