Natural Language Processing news and analysis on Web Pulse: 5440 curated articles tracking the latest Natural Language Processing developments, tools, and research, updated continuously from vetted sources.
Gartner posted an on-site Data Scientist role in Gurgaon requiring 3-6 years of applied ML/AI experience, with no salary published. The position covers classical machine learning, NLP, and LLM/agentic systems including R…
A new design guide proposes an application pattern for keeping voice agents useful during slow backend tool calls, requiring explicit task states such as pending, running, completed, failed and uncertain, and tracking a …
Researchers are exploring AI tools that analyze speech patterns to help diagnose schizophrenia, a condition that is often difficult to identify. The article from Knowable Magazine highlights ongoing efforts to use machin…
Apple announced that iOS 27 will launch on Monday, September 14, with release notes detailing new AI features including a more capable Siri, Apple Intelligence enhancements across Photos, Safari, and other apps, and supp…
A developer built a hybrid search system using Node.js's built-in node:sqlite module and SQLite's FTS5, eliminating the need for native dependencies like better-sqlite3. The system combines lexical search with optional v…
Researchers introduced ReCite, a decoupled agentic framework that uses claim-level reasoning to improve citation accuracy in academic writing, outperforming state-of-the-art massive generative models in strict citation a…
A developer has created an AI-powered lead qualification workflow using n8n, which automates the process of receiving, analyzing, and scoring leads from unstructured messages. The workflow uses a webhook to capture enqui…
Stas, director of Just Tools LTD, the company behind Clavio, an AI dictation app for Mac, shares six spoken brief structures for coding assistants. The briefs aim to improve communication with AI coding tools by providin…
A newly published patent-pending technology at TRL 3 describes an AI-powered system that ingests large-scale patent databases and converts patent records into vector embeddings for semantic similarity search and prior-ar…
DoBox, a company developing an AI-powered email assistant, argues that while extracting tasks from messages is now standard, the more valuable and unsolved problem is capturing non-task facts—such as 'Ridgeway declined o…
Researchers at SUNY Albany have developed GrantsMate, an AI-powered research support platform that combines funding discovery, collaborator identification, and institutional policy guidance into a single conversational s…
Gradium, the Paris-based voice AI company spun out of the Kyutai research lab, launched Voice Design, a tool that generates new synthetic voices from a text description in seconds, live in its API and Studio. In a vendor…
Hugging Face offers a free, ad-free course on large language models (LLMs) and natural language processing (NLP) using its ecosystem, including Transformers, Datasets, Tokenizers, and Accelerate, as well as the Hugging F…
A developer built Video Transcriber Pro, a desktop tool that transcribes video and audio locally using OpenAI's Whisper model, ensuring sensitive material never leaves the machine. The pipeline integrates yt-dlp, ffmpeg,…
ServiceNow AI has released EVA-Bench Data 2.0, an enterprise-grade benchmark for voice agents that expands from a single domain to three major enterprise scenarios: airline customer service, IT service management, and he…
Microsoft released MAI-Transcribe-2 on September 3rd, a speech-to-text model priced at $0.10 per audio hour, claiming a 5.2% average word error rate on the FLEURS benchmark across 60 languages and processing at roughly 4…
A freelance translator's accidental experiment with ChatGPT and Claude found that both AI chatbots degrade on longer documents, require constant coaching, invent plausible-sounding but false terminology, and exhibit cult…
SoundNativ, an AI-powered English pronunciation app, reports that 86% of its 70,000+ users see improvement in 12 weeks, offering 500+ video lessons, 20,000+ speaking exercises, and 500+ real conversations with instant so…
Google has introduced Gemini 3.5 Transcribe, a speech-to-text model that enables voice-driven workflows on macOS, allowing users to summarize local files, reuse text across apps, and generate images via voice commands wi…
A developer built a controllable voice companion using Tencent RTC's Conversational AI, replacing an autonomous agent loop with deterministic state-machine control to avoid unintended actions. The architecture separates …