asya: Mindful verbal communication using deep learning

08/20/2020
by   Evalds Urtans, et al.
0

asya is a mobile application that consists of deep learning models which analyze spectra of a human voice and do noise detection, speaker diarization, gender detection, tempo estimation, and classification of emotions using only voice. All models are language agnostic and capable of running in real-time. Our speaker diarization models have accuracy over 95 These models can be applied for a variety of areas like customer service improvement, sales effective conversations, psychology and couples therapy.

READ FULL TEXT
research
10/25/2021

Controllable and Interpretable Singing Voice Decomposition via Assem-VC

We propose a singing decomposition system that encodes time-aligned ling...
research
08/08/2020

JukeBox: A Multilingual Singer Recognition Dataset

A text-independent speaker recognition system relies on successfully enc...
research
07/12/2022

NEC: Speaker Selective Cancellation via Neural Enhanced Ultrasound Shadowing

In this paper, we propose NEC (Neural Enhanced Cancellation), a defense ...
research
11/15/2022

Rapid Connectionist Speaker Adaptation

We present SVCnet, a system for modelling speaker variability. Encoder N...
research
10/24/2020

Stop Bugging Me! Evading Modern-Day Wiretapping Using Adversarial Perturbations

Mass surveillance systems for voice over IP (VoIP) conversations pose a ...
research
05/11/2020

End-To-End Speech Synthesis Applied to Brazilian Portuguese

Voice synthesis systems are popular in different applications, such as p...
research
07/13/2019

Towards Robust Voice Pathology Detection

Automatic objective non-invasive detection of pathological voice based o...

Please sign up or login with your details

Forgot password? Click here to reset