Automatic transcription of Broadcast News

نویسندگان

  • Scott Saobing Chen
  • Ellen Eide
  • Mark J. F. Gales
  • Ramesh A. Gopinath
  • D. Kanvesky
  • Peder A. Olsen
چکیده

This paper describes the IBM approach to Broadcast News Transcription. Typical problems in the Broadcast News Transcription task are segmentation, clustering, acoustic modeling, language modeling and acoustic model adaptation. This paper presents new algorithms for each of these focus problems. Some key ideas include Bayesian Information Criterion (for segmentation, clustering and acoustic modeling) and Speaker/Cluster Adapted Training. Abstract Dieser Beitrag beschreibt ein bei IBM entwickeltes Verfahren zur Tranksription von Rundfunknachrichten. Zu den typischen Problemen der Transkription gehoeren die Segmentierung, Clusterung, akustische Modellierung, Sprachmodellierung und akustische Modelladaption. In disem Beitrag werden neuartige Algorithmen fuer diese einzelnen Probleme praesentiert. Als einige der hier enthaltenen Schluesselideen koennen das Kriterium der Bayes’schen Information (zur Segmentierung, Clusterung and akustischen Modellierung) sowie sprecherund clusteradaptives Training genannt werden.Dieser Beitrag beschreibt ein bei IBM entwickeltes Verfahren zur Tranksription von Rundfunknachrichten. Zu den typischen Problemen der Transkription gehoeren die Segmentierung, Clusterung, akustische Modellierung, Sprachmodellierung und akustische Modelladaption. In disem Beitrag werden neuartige Algorithmen fuer diese einzelnen Probleme praesentiert. Als einige der hier enthaltenen Schluesselideen koennen das Kriterium der Bayes’schen Information (zur Segmentierung, Clusterung and akustischen Modellierung) sowie sprecherund clusteradaptives Training genannt werden. Abstract Cet article décrit l’approche d’IBM pour la transcription des nouvelles du journal télévisé. Les problèmes caractéristiques de cette tâche sont la segmentation, la classification automatique, la modélisation acoustique, l’estimation de modèles de langage et l’adaptation des modèles acoustiques. Cet article présente de nouveaux algorithmes pour chacun de ces problèmes. Parmi les idées clés, on peut citer le critère d’information Bayesien (pour la segmentation, la classification automatique et la modélisation acoustique) et l’apprentissage adapté pour chaque locuteur/classe de locuteurs.Cet article décrit l’approche d’IBM pour la transcription des nouvelles du journal télévisé. Les problèmes caractéristiques de cette tâche sont la segmentation, la classification automatique, la modélisation acoustique, l’estimation de modèles de langage et l’adaptation des modèles acoustiques. Cet article présente de nouveaux algorithmes pour chacun de ces problèmes. Parmi les idées clés, on peut citer le critère d’information Bayesien (pour la segmentation, la classification automatique et la modélisation acoustique) et l’apprentissage adapté pour chaque locuteur/classe de locuteurs.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Real-time recognition of broadcast news

Although the performance of state-of-the-art automatic speech recognition systems on the challenging task of broadcast news transcription has improved considerably in recent years, many of the systems operate in 130-300 times real-time [1]. Many applications of automatic transcription of broadcast news, eg. closedcaption subtitles for television broadcasts, require real-time operation. This pap...

متن کامل

TUKE-BNews-SK: Slovak Broadcast News Corpus Construction and Evaluation

This article presents an overview of the existing acoustical corpuses suitable for broadcast news automatic transcription task in the Slovak language. The TUKE-BNews-SK database created in our department was built to support the application development for automatic broadcast news processing and spontaneous speech recognition of the Slovak language. The audio corpus is composed of 479 Slovak TV...

متن کامل

Toward Automatic Recognition of Japanese Broadcast News

In this paper we report on automatic recognition of Japanese broadcast-news speech. We have been working on largevocabulary continuous speech recognition (LVCSR) for Japanese newspaper speech transcription and achieved reasonably good performance. We have recently applied our LVCSR system to transcribing Japanese broadcast-news speech. We extended the vocabulary to 20k words and trained the lan...

متن کامل

Toward automatic transcription of Japanese broadcast news

In this paper, we report on the automatic recognition of Japanese broadcast-news speech. We have been working on largevocabulary continuous speech recognition (LVCSR) for Japanese newspaper speech transcription and have achieved good performance. We have recently applied our LVCSR system to transcribing Japanese broadcast-news speech. We extended the vocabulary from 7k words to 20k words and tr...

متن کامل

Advances in automatic transcription of Italian broadcast news

This paper presents some recent improvements in automatic transcription of Italian broadcast news obtained at ITCirst. A first preliminary activity was carried out in order to develop a suitable speech corpus for the Italian language. The resulting corpus, formed by recordings covering 30 hours of radio news, was exploited for developing a baseline system for transcription of broadcast news. Th...

متن کامل

Japanese broadcast news transcription

In this paper, we describe the on-going development of a Japanese Broadcast News Transcription system at BBN Technologies. This is a collaboration between BBN and NHK to use automatic speech recognition technology to provide live closed caption for NHK’s TV news programs in Japan. We describe what the NHK Broadcast News Corpus comprises and how we adopted transcription technology developed for ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Speech Communication

دوره 37  شماره 

صفحات  -

تاریخ انتشار 2002