DeepAI AI Chat
Log In Sign Up

End-to-End Multi-speaker ASR with Independent Vector Analysis

by   Robin Scheibler, et al.

We develop an end-to-end system for multi-channel, multi-speaker automatic speech recognition. We propose a frontend for joint source separation and dereverberation based on the independent vector analysis (IVA) paradigm. It uses the fast and stable iterative source steering algorithm together with a neural source model. The parameters from the ASR module and the neural source model are optimized jointly from the ASR loss itself. We demonstrate competitive performance with previous systems using neural beamforming frontends. First, we explore the trade-offs when using various number of channels for training and testing. Second, we demonstrate that the proposed IVA frontend performs well on noisy data, even when trained on clean mixtures only. Furthermore, it extends without retraining to the separation of more speakers, which is demonstrated on mixtures of three and four speakers.


page 1

page 2

page 3

page 4

page 5


Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR

Most approaches to multi-talker overlapped speech separation and recogni...

Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization

This paper proposes a new paradigm for handling far-field multi-speaker ...

End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning

This paper presents our latest investigation on end-to-end automatic spe...

Multi-Channel Multi-Speaker ASR Using 3D Spatial Feature

Automatic speech recognition (ASR) of multi-channel multi-speaker overla...

Multi-scenario deep learning for multi-speaker source separation

Research in deep learning for multi-speaker source separation has receiv...

Tackling real noisy reverberant meetings with all-neural source separation, counting, and diarization system

Automatic meeting analysis is an essential fundamental technology requir...

Data-Driven Source Separation Based on Simplex Analysis

Blind source separation (BSS) is addressed, using a novel data-driven ap...