IEEE

End-to-End Target Speaker Speech Recognition Using Context-Aware Attention Mechanisms for Challenging Enrollment Scenario

Abstract: This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and ...
GitHub

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously ...
Wired

Meta Tapped a Pentagon Supplier to Prototype Face Recognition for Its Glasses

Rank One, whose board includes a former CIA deputy director and a former FBI science chief, supplied face recognition to Meta for internal development of its smart glasses app. Meta is testing ...
IEEE

FPGA Implementation of PoolFormer Network Using Python-Driven High-Level Synthesis Framework for Edge-AIoT Speech Recognition

Abstract: This brief presents an edge-AIoT speech recognition system, which is based on a new spiking feature extraction (SFE) method and a PoolFormer (PF) neural network optimized for implementation ...
GitHub

WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation

This is the official repository 👑 for the WenetSpeech-Yue dataset and the source code for WenetSpeech-Pipe speech data preprocessing pipeline. To address the unique linguistic characteristics of ...
Innovation & Tech Today

Meta Removes Facial Recognition Code From Smart Glasses App Following Privacy Backlash

This week, Meta removed facial recognition code from its Meta AI companion app after reporting by WIRED revealed that the company had already embedded substantial portions of an unreleased facial ...