Termsslug: speaker-diarization

Speaker Diarization

说话人分离

Technique that segments and labels distinct speakers within multi-speaker audio.

Curated Intelligence

10 items · Page 1/1
IT之家 · 智能时代T2·Models
72 pts
iFlytek Opens SparkAudio 1.0 Speech Foundation Model API with 99-Language Support

iFlytek has launched API access to SparkAudio 1.0, its speech foundation model, on the iFlytek Open Platform. The model understands speech end-to-end instead of the cascaded transcribe-then-reason pipeline, covering 99 languages and 202 dialects across transcription, translation, speaker diarization, emotion analysis and audio QA, and is trained entirely on domestic compute.

IT之家 · 智能时代T2·Models
85 pts
NVIDIA Open-Sources Nemotron 3.5 Transcribe for Multilingual Overlapping Speech

NVIDIA released the open-weight speech model Nemotron 3.5 Transcribe, featuring an MoE architecture that supports 40 languages and precise transcription/diarization of up to 8 overlapping speakers. The model tops several open-source benchmarks and comes with the Granary v2 data pipeline, targeting use cases like meeting minutes and customer service.

Marktechpost (@Marktechpost)T2·Models
78 pts
NVIDIA Releases Nemotron 3.5 Transcribe with Instruction-Driven ASR

NVIDIA released Nemotron 3.5 Transcribe, a speech LLM built on a hybrid Mamba-Transformer MoE architecture. It integrates a frozen diarizer with an ASR encoder to enable instruction-driven transcription, allowing users to control output formats (verbatim, written, translation) via text prompts. While it outperforms Qwen3-ASR in English benchmarks, it is offline-only and shows lower accuracy for Mandarin far-field meetings.

The DecoderT2·Models
78 pts
Nvidia Releases Open Nemotron 3.5 Transcribe for Multilingual Speech Tasks

Nvidia released the open-source speech model Nemotron 3.5 Transcribe, which integrates transcription, translation, and speaker recognition for up to 40 languages. Utilizing a Mixture-of-Experts architecture (30B total parameters, 4B active), it runs on a single GPU and achieves top-tier benchmark results. The release also includes the Granary v2 dataset with 844,000 hours of audio and tools for domain-specific adaptation.

InfoQ 中文T2·Models
68 pts
iFlytek Launches SparkAudio 1.0 for Unified Audio Understanding

iFlytek released SparkAudio 1.0, a foundational speech model that unifies complex audio understanding, emotion recognition, and real-time speaker separation, overcoming information loss in traditional cascaded architectures. The upgraded X2.6 series includes a 4B on-device model achieving ~70% of cloud capabilities with low latency. With voice LLM API calls surging over 20x year-on-year, this marks a shift from simple text transcription to multi-source acoustic-semantic joint reasoning.

TechCrunch AIT2·Industry
45 pts
Nirva Raises $33M for Pendant That Only Listens to Wearer

AI hardware startup Nirva announced a $25 million pre-Series A round, bringing its total funding to $33 million. Founded by ex-Meta Reality Labs employees, the company is launching a jewelry-like pendant that uses voice separation technology to listen only to the wearer, addressing privacy concerns in ambient AI devices.

Qwen 官方博客 (通义)T1·Models
78 pts
Qwen3.8-LiveTranslate Launches: New Architecture Cuts Latency to 2.3s

The Qwen team released Qwen3.8-LiveTranslate, reducing average latency (LAAL) in real-time interpretation from 2.8s to 2.3s via a new Interleave audio-text architecture. Building on support for 60 languages, the model introduces real-time speaker diarization, synchronized source-target output, and long-context disambiguation to enhance accuracy and voice cloning stability in multi-speaker scenarios.

Hugging Face BlogT1·Tools
35 pts
HF Endpoints Integrate ASR and Speculative Decoding

Hugging Face Inference Endpoints demonstrates a solution combining ASR, diarization, and speculative decoding. The case aims to improve speech transcription efficiency and accuracy but lacks specific performance metrics or detailed reusable configuration guides.