SpeakerBeam: A New Deep Learning Technology for Extracting Speech of a Target Speaker Based on the Speaker's Voice Characteristics

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU149376" target="_blank" >RIV/00216305:26230/18:PU149376 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.ntt-review.jp/archive/ntttechnical.php?contents=ntr201811all.pdf&mode=show_pdf" target="_blank" >https://www.ntt-review.jp/archive/ntttechnical.php?contents=ntr201811all.pdf&mode=show_pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

SpeakerBeam: A New Deep Learning Technology for Extracting Speech of a Target Speaker Based on the Speaker's Voice Characteristics

Popis výsledku v původním jazyce

In a noisy environment such as a cocktail party, humans can focus on listening to a desired speaker, an ability known as selective hearing. Current approaches developed to realize computational selective hearing require knowing the position of the target speaker, which limits their practical usage. This article introduces SpeakerBeam, a deep learning based approach for computational selective hearing based on the characteristics of the target speakers voice. SpeakerBeam requires only a small amount of speech data from the target speaker to compute his/her voice characteristics. It can then extract the speech of that speaker regardless of his/her position or the number of speakers talking in the background.

Název v anglickém jazyce

SpeakerBeam: A New Deep Learning Technology for Extracting Speech of a Target Speaker Based on the Speaker's Voice Characteristics

Popis výsledku anglicky

In a noisy environment such as a cocktail party, humans can focus on listening to a desired speaker, an ability known as selective hearing. Current approaches developed to realize computational selective hearing require knowing the position of the target speaker, which limits their practical usage. This article introduces SpeakerBeam, a deep learning based approach for computational selective hearing based on the characteristics of the target speakers voice. SpeakerBeam requires only a small amount of speech data from the target speaker to compute his/her voice characteristics. It can then extract the speech of that speaker regardless of his/her position or the number of speakers talking in the background.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

NTT Technical Review

ISSN

1348-3447

e-ISSN

—

Svazek periodika

16

Číslo periodika v rámci svazku

11

Stát vydavatele periodika

JP - Japonsko

Počet stran výsledku

6

Strana od-do

19-24

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85057190849