Saved in:
Bibliographic Details
Main Authors: Cui, Can, Sheikh, Imran Ahamad, Sadeghi, Mostafa, Vincent, Emmanuel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.06570
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910589650993152
author Cui, Can
Sheikh, Imran Ahamad
Sadeghi, Mostafa
Vincent, Emmanuel
author_facet Cui, Can
Sheikh, Imran Ahamad
Sadeghi, Mostafa
Vincent, Emmanuel
contents Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data. We present a novel study aiming to optimize the use of a Speaker-Attributed ASR (SA-ASR) system in real-life scenarios, such as the AMI meeting corpus, for improved speaker assignment of speech segments. First, we propose a pipeline tailored to real-life applications involving Voice Activity Detection (VAD), Speaker Diarization (SD), and SA-ASR. Second, we advocate using VAD output segments to fine-tune the SA-ASR model, considering that it is also applied to VAD segments during test, and show that this results in a relative reduction of Speaker Error Rate (SER) up to 28%. Finally, we explore strategies to enhance the extraction of the speaker embedding templates used as inputs by the SA-ASR system. We show that extracting them from SD output rather than annotated speaker segments results in a relative SER reduction up to 20%.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06570
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
Cui, Can
Sheikh, Imran Ahamad
Sadeghi, Mostafa
Vincent, Emmanuel
Computation and Language
Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data. We present a novel study aiming to optimize the use of a Speaker-Attributed ASR (SA-ASR) system in real-life scenarios, such as the AMI meeting corpus, for improved speaker assignment of speech segments. First, we propose a pipeline tailored to real-life applications involving Voice Activity Detection (VAD), Speaker Diarization (SD), and SA-ASR. Second, we advocate using VAD output segments to fine-tune the SA-ASR model, considering that it is also applied to VAD segments during test, and show that this results in a relative reduction of Speaker Error Rate (SER) up to 28%. Finally, we explore strategies to enhance the extraction of the speaker embedding templates used as inputs by the SA-ASR system. We show that extracting them from SD output rather than annotated speaker segments results in a relative SER reduction up to 20%.
title Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications
topic Computation and Language
url https://arxiv.org/abs/2403.06570