Prominence-aware automatic speech recognition for conversational speech

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Linke, Julian, Schuppler, Barbara
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916947413696512
author Linke, Julian
Schuppler, Barbara
author_facet Linke, Julian
Schuppler, Barbara
contents This paper investigates prominence-aware automatic speech recognition (ASR) by combining prominence detection and speech recognition for conversational Austrian German. First, prominence detectors were developed by fine-tuning wav2vec2 models to classify word-level prominence. The detector was then used to automatically annotate prosodic prominence in a large corpus. Based on those annotations, we trained novel prominence-aware ASR systems that simultaneously transcribe words and their prominence levels. The integration of prominence information did not change performance compared to our baseline ASR system, while reaching a prominence detection accuracy of 85.53% for utterances where the recognized word sequence was correct. This paper shows that transformer-based models can effectively encode prosodic information and represents a novel contribution to prosody-enhanced ASR, with potential applications for linguistic research and prosody-informed dialogue systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10116
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prominence-aware automatic speech recognition for conversational speech
Linke, Julian
Schuppler, Barbara
Computation and Language
Audio and Speech Processing
This paper investigates prominence-aware automatic speech recognition (ASR) by combining prominence detection and speech recognition for conversational Austrian German. First, prominence detectors were developed by fine-tuning wav2vec2 models to classify word-level prominence. The detector was then used to automatically annotate prosodic prominence in a large corpus. Based on those annotations, we trained novel prominence-aware ASR systems that simultaneously transcribe words and their prominence levels. The integration of prominence information did not change performance compared to our baseline ASR system, while reaching a prominence detection accuracy of 85.53% for utterances where the recognized word sequence was correct. This paper shows that transformer-based models can effectively encode prosodic information and represents a novel contribution to prosody-enhanced ASR, with potential applications for linguistic research and prosody-informed dialogue systems.
title Prominence-aware automatic speech recognition for conversational speech
topic Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2509.10116