The article explains how to develop a speaker‑recognition application using Claude code or Codex, focusing on practical coding techniques for building an internal tool. It provides step‑by‑step guidance on implementing the necessary components and integrating them into a functional app. The post serves as a tutorial for developers looking to create voice‑based authentication or identification systems.
arXiv:1707. 00835v1 Announce Type: cross Abstract: This contribution gives an overview of face recogni-tion algorithms, their implementation and practical uses.
arXiv:2606. 16505v1 Announce Type: cross Abstract: Understanding speaker confidence is crucial in educational settings, as it can enhance personalised feedback and improve learning outcomes.
Google has launched two new Gemini text‑to‑speech models—gemini‑3.8‑flash‑tts and gemini‑3.8‑flash‑lite‑tts—offering a library of over 2,000 voices and the option to create a custom voice from a 30‑second audio sample. The author built a playground interface that lets users define multi‑character conversations with distinct voices and styles, and demonstrated it with a scripted dialogue between two pelicans. Generating 1 minute 18 seconds of audio with the Flash model took about 20 seconds and cost 2.74 cents.
FASTDIAR is a frame‑level speaker encoder designed for real‑time streaming diarization on a single CPU thread. It converts a state‑of‑the‑art speaker recognition architecture into a causal model that emits an embedding every 80 ms from a two‑second window, and pairs it with online clustering that updates only when the stream’s self‑similarity changes. Trained via distillation from an utterance‑level teacher, it achieves the highest accuracy on low‑overlap benchmarks, degrades less with more speakers, and runs five times faster than real time.
arXiv:2607. 18704v1 Announce Type: cross Abstract: Caption Studio is a transparency-first speech and audio intelligence platform that transforms spoken audio and video into structured, searchable content through automated transcription, speaker diarization, speech analytics, signal-level audio analysis, and subtitle generation.
Speaker recognition has advanced rapidly with large-scale training datasets, yet Vietnamese remains under-resourced, with existing corpora limited in scale and acoustic diversity. Most large-scale datasets rely on facial cues to link speech with speaker identities, restricting data collection to recordings where speakers appear on camera.
The paper describes Transsion Speech Team’s submission to Task 1 of the MLC‑SLM 2026 Challenge, aiming at speaker‑attributed transcription for multilingual conversational speech. Their cascaded framework includes a DiariZen‑based speaker diarization module, a Qwen3‑Omni‑based long‑form multilingual ASR module with CTC alignment for precise timestamps, and a fusion module that merges diarization and transcription outputs into speaker‑attributed STM results. On the official evaluation set, the system achieved a tcpMER of 15.41% and secured second place among all participants.
For the first time, developers can also instruct the text-to-speech model to speak in a specific way—for example, “talk like a sympathetic customer service agent”—unlocking a new level of customization for voice agents.
Detecting phonemes from children's speech has historically been difficult due to the scarcity of training data, and unique characteristics of children's speech. During a phoneme detection competition, we found that training a lightweight model to predict the age of the learner, as well as the phoneme sequence, enabled a 94M-parameter model to outperform WavLM Large models (317M) on the target DrivenData distribution, and fall within approximately 0.