Multi-Speaker

Machine Listening Skill

 

Recognize multiple speakers, identify languages, emotions & intents from natural conversations (meetings, interviews, calls). 

 
robot_human3.png

Enrich your ASR with DeepAffects

 
 

1. extract HUMAN CONVERSATIONS FROM AUDIO

 

2. rECOGNISE SPEAKERS, identify EMOTIONS & INTENTS

deepaffects-logo.png
 

3. combine deepaffects insights WITH ASR to enhance the ENTERPRISE APPLICATIONS

enterpris-apps-icon.png
 
F2F2F2.png

Multi-Speaker Machine Listening for Voice-Apps

CALL CENTER APPS

callcenter-icon1 (1).png

Identify agent & customer voice, sentiments & intents to measure customer satisfaction & generate personalized agent coaching.

HEALTHCARE APPS

mental-health (1).png

Extract prosodic features to build high specificity & sensitivity deep neural nets based models to screen & monitor patients for mental & respiratory illness. 

TRANSCRIPTION APPS

image+(2).png

Enhance accuracy of the interview, conference, meeting transcripts by removing noise and recognizing multiple speakers.

MEETING APPS

image+(1).png

Recognize multiple speakers & their intents in a meeting to monitor dynamics and equity of contribution/participation in meetings.  

cfd8dc.png

Our approach differentiates us

 
 Ann Liu

Speech Enhancement

 Sean Edwards

Spectral Analysis VS Speech-to-text

 Phyllis Mitchell

Multi-Speaker (>= 2) in the wild

 Emily Hernandez

multi-lingual

 Judith Rhee

Short & Long utterance

 Janet Howard

Robust DNN based Features

 Janet Cho

Large Training dataset

 Diana Garcia

Balanced training dataset to remove bias

 John Lee

Clustering algorithm with Anomaly Detection

 Gary Ward

Domain specific Intent Detection

 Phyllis Amirpour

infinitely scalable

 Donald Jenkins

secured

F2F2F2.png