GENRE EFFECTS ON AUTOMATIC SENTENCE SEGMENTATION OF SPEECH: A COMPARISON OF BROADCAST NEWS AND BROADCAST CONVERSATIONS

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F09%3A00501546" target="_blank" >RIV/49777513:23520/09:00501546 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

GENRE EFFECTS ON AUTOMATIC SENTENCE SEGMENTATION OF SPEECH: A COMPARISON OF BROADCAST NEWS AND BROADCAST CONVERSATIONS

Popis výsledku v původním jazyce

We investigate genre effects on the task of automatic sentence segmentation, focusing on two important domains - broadcast news (BN) and broadcast conversation (BC). We employ an HMM model based on textual and prosodic information and analyze differencesin segmentation accuracy and feature usage between the two genres using both manual and automatic speech transcripts. Experiments are evaluated using Czech broadcast corpora annotated for sentence-like units (SUs). Prosodic features capture informationabout pause, duration, pitch, and energy patterns. Textual knowledge sources include words, part-of-speech, and automatically induced classes. We also analyze effects of using additional textual data that is not annotated for SUs. Feature analysis reveals significant differences in both textual and prosodic feature usage patterns between the two genres. The analysis is important for building automatic understanding systems when limited matched-genre data are available, or for designing e

Název v anglickém jazyce

GENRE EFFECTS ON AUTOMATIC SENTENCE SEGMENTATION OF SPEECH: A COMPARISON OF BROADCAST NEWS AND BROADCAST CONVERSATIONS

Popis výsledku anglicky

We investigate genre effects on the task of automatic sentence segmentation, focusing on two important domains - broadcast news (BN) and broadcast conversation (BC). We employ an HMM model based on textual and prosodic information and analyze differencesin segmentation accuracy and feature usage between the two genres using both manual and automatic speech transcripts. Experiments are evaluated using Czech broadcast corpora annotated for sentence-like units (SUs). Prosodic features capture informationabout pause, duration, pitch, and energy patterns. Textual knowledge sources include words, part-of-speech, and automatically induced classes. We also analyze effects of using additional textual data that is not annotated for SUs. Feature analysis reveals significant differences in both textual and prosodic feature usage patterns between the two genres. The analysis is important for building automatic understanding systems when limited matched-genre data are available, or for designing e

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2009

Kód důvěrnosti údajů

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

Název statě ve sborníku

2009 IEEE International Conference on Acoustics, Speech, and Signal Processing

ISBN

978-1-4244-2353-8

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

—

Název nakladatele

IEEE

Místo vydání

Bryan, TX

Místo konání akce

Taipei, Taiwan

Datum konání akce

25. 4. 2009

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000268919202250