Green Matters on MSN

What Do Wolves' Howling in Yellowstone Mean? Scientists Use AI to Decode the Sound

Now, the researchers at Yellowstone National Park want to learn wolf language beyond what has been fed to us through ...
GitHub

GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning

GLM-TTS is a high-quality text-to-speech (TTS) synthesis system based on large language models, supporting zero-shot voice cloning and streaming inference. This system adopts a two-stage architecture: ...
the-decoder

OpenAI releases new models for its Realtime API

OpenAI has updated its Realtime API with three new model snapshots designed to improve transcription, speech synthesis, and function calling. According to developers, the gpt-4o-mini-transcribe ...
GitHub

liutaocode/TTS-arxiv-daily

2025-10-28 Bayesian Speech synthesizers Can Learn from Multiple Teachers Ziyang Zhang et.al. 2510.24372 null 2025-10-28 emg2speech: synthesizing speech from electromyography using self-supervised ...
the-decoder

Making AI sound human comes at the cost of meaning, researchers show

Researchers at the University of Zurich found that AI-generated text can still be reliably distinguished from human writing. Their study shows that efforts to make models sound more natural often ...
IEEE

Boundary-Aware Network With Two-Stage Partial Decoders for Salient Object Detection in Remote Sensing Images

Abstract: Salient object detection (SOD) is a binary pixelwise classification to distinguish objects in an image and also has attracted many research interests in the optical remote sensing images ...
IEEE

Recurrent Encoder–Decoder Networks for Vessel Trajectory Prediction With Uncertainty Estimation

Abstract: Recent deep learning methods for vessel trajectory prediction are able to learn complex maritime patterns from historical automatic identification system (AIS) data and accurately predict ...
Microsoft

VALL-E Family

With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis. However, sampling ...