Speaker-Aware Training of Attention-Based End-to-End Speech Recognition Using Neural Speaker Embeddings

Aku Rouhe; Tuomas Kaseva; Mikko Kurimo

doi:10.1109/icassp40776.2020.9053998

ScienceGate Book Chapters

JOURNAL ARTICLE

Speaker-Aware Training of Attention-Based End-to-End Speech Recognition Using Neural Speaker Embeddings

Aku Rouhe Tuomas Kaseva Mikko Kurimo

Year: 2020 Pages: 7064-7068

DOI: 10.1109/icassp40776.2020.9053998

Get Full-Text PDF Get Analytical Report

Abstract

| openaire: EC/H2020/780069/EU//MeMAD

Keywords:

Embedding Computer science Speech recognition Leverage (statistics) Speaker recognition End-to-end principle Speaker diarisation Deep neural networks Artificial neural network Training set Speaker verification Artificial intelligence Pattern recognition (psychology)

Metrics

Cited By

0.44

FWCI (Field Weighted Citation Impact)

Refs

0.67

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Speech Recognition and Synthesis

Physical Sciences → Computer Science → Artificial Intelligence

Speech and Audio Processing

Physical Sciences → Computer Science → Signal Processing

Music and Audio Processing

Physical Sciences → Computer Science → Signal Processing

Speaker-Aware Training of Attention-Based End-to-End Speech Recognition Using Neural Speaker Embeddings

Abstract

Metrics

Citation History

Topics

Related Documents

Personality-aware Training based Speaker Adaptation for End-to-end Speech Recognition

Speaker Adaptation for Attention-Based End-to-End Speech Recognition

Deep neural network-based speaker embeddings for end-to-end speaker verification

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

End-to-End Multi-Speaker Speech Recognition