Michael Mark Goodwin

Clock skew robust acoustic echo cancellation

Real-time summary evaluation large language model

Face-aware relighting of live video content

Sentiment-based conversation hotspot detection

MANIFOLD LEARNING FOR SOUND FIELD ESTIMATION

Set-based active speaker detection

Semi-supervised training of a machine learning model for target speaker audio enhancement

Machine learning model that estimates human audio quality assessments

Manifold learning for sound field estimation

EFFICIENT VOICE SYNTHESIS USING FRAME-BASED PROCESSING

PROMPT MANAGEMENT FOR LARGE LANGUAGE MODEL

Efficient voice synthesis using frame-based processing

Bidirectional videoconference-related messaging for public switched telephone network participants

UNIFIED AUDIO SUPPRESSION MODEL

Separate representations of videoconference participants that use a shared device

Multi-Talker Audio Stream Separation, Transcription and Diaraization

Joint noise and echo suppression for two-way audio communication enhancement

Videoconference content sharing for public switched telephone network participants

Real-time low-complexity stereo speech enhancement with spatial cue preservation