Pronunciation variants across system configuration, language and speaking style

نویسندگان

  • Martine Adda-Decker
  • Lori Lamel
چکیده

This contribution aims at evaluating the use of pronunciation variants for di erent recognition system con gurations, languages and speaking styles. This study is limited to the use of variants during speech alignment, given an orthographic transcription of the utterance and a phonemically represented lexicon, and is thus focused on the modeling capabilities of the acoustic word models. To measure the need for variants we have de ned the variant2+ rate which is the percentage of words in the corpus not aligned with the most commonphonemic transcription. This measure may be indicative of the possible need for pronunciation variants in the recognition system. Pronunciation lexica have been automatically created so as to include a large number of variants (overgeneration). In particular, lexica with parallel and sequential variants were automatically generated in order to assess the spectral and temporal modeling accuracy. We rst investigated the dependence of the aligned variants on the recognizer con guration. Then a cross-lingual study was carried out for read speech in French and American English using the BREF and the WSJ corpora. A comparison between read and spontaneous speech was made for French based on alignments of BREF (read) and Mask (spontaneous) data. Comparative alignment results using di erent acoustic model sets demonstrate the dependency between the acoustic model accuracy and the need for pronunciation variants. The alignment results obtained with the above lexica have been used to study the link between word frequencies and variants using di erent acoustic model sets. Cette contribution vise a evaluer l'utilisation des variantes de prononciation pour di erentes congurations de syst eme, di erentes langues et di erents types d' elocution. Cette etude se limite a l'utilisation de variantes pendant l'alignement automatique de la parole etant donn ee une transcription orthographique correcte et un lexique de prononciation. Nous focalisons ainsi notre etude sur la capacit e des mod eles acoustique des mots a rendre compte du signal observ e. Pour evaluer le besoin de variantes nous avons d e ni le taux de variant2+ qui correspond au pourcentage de mots du corpus qui ne sont pas align es avec la meilleure transcription phon emique. Ce taux peut être consid er e comme indicatif d'un eventuel besoin de variantes de prononciation dans le syst eme de reconnaissance. Di erents lexiques de prononciation ont et e cr e es automatiquement g en erant di erents types et quantit es de variantes (avec surg en eration). En particulier des lexiques avec des variantes parall eles et s equentielles ont et e distingu es a n d' evaluer la pr ecision de la mod elisation spectrale et temporelle. 5 Dans une premi ere etape nous avons montr e le lien entre le besoin de variantes de prononciation et la qualit e des mod eles acoustiques. Nous avons ensuite compar e di erents ph enom enes de variantes pour l'anglais et le fran cais sur des grands corpus de parole lue (WSJ et BREF). Une comparaison entre parole spontan ee et parole lue est pr esent ee. Cette etude montre que le besoin de variantes diminue avec la pr ecision des mod eles acoustiques. Pour le fran cais, elle permet de r ev eler l'importance des variantes s equentielles, en particulier du e-muet.

برای دانلود 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

Pronunciation Variants Across Systems, Languages and Speaking Style

This contribution aims at evaluating the use of pronunciation variants across different system configurations, languages and speaking styles. This study is limited to the use of variants during speech alignment, given an orthographic transcription and a phonemically represented lexicon, thus focusing on the modeling abilities of the acoustic word models. Parallel and sequential variants are tes...

متن کامل

Unsupervised Pronunciation Adaptation for Off-line Transcription of Japanese Lecture Speeches

Observing that most variations in pronunciation are strongly speaker and speaking style dependent, and that the introduction of pronunciation variants in a speaker-independent recognition system is of limited success, we refrain from applying multiple pronunciation variants in the speakerindependent case and instead introduce pronunciation variants without supervision when specializing the reco...

متن کامل

Pronunciation variant analysis using speaking style parallel corpus

To improve the recognition accuracy for spontaneous conversational speech, we collected a corpus to study how spontaneous conversational speech differs from read style speech. The corpus consists of two parts: 1) spontaneous conversational speech and 2) read speech with the same word transcriptions as the conversational speech. In word and phone recognition experiments, it was confirmed that, f...

متن کامل

Evaluation of Pronunciation Variants in the ASR Lexicon for Different Speaking Styles

One of the challenges in automatic speech recognition is how to handle pronunciation variation. The main causes for pronunciation variation are the speaker (voice characteristics, accent, non-nativeness etc.) and the speaking style (reading, spontaneous responses, conversation etc.). An ASR system has basically two options for modelling the variation on the word and sub-word level: lexical mode...

متن کامل

Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition

In spontaneous conversational speech there is a large amount of variability due to accents, speaking styles and speaking rates (also known as the speaking mode) [3]. Because current recognition systems usually use only a relatively small number of pronunciation variants for the words in their dictionaries, the amount of variability that can be modeled is limited. Increasing the number of varian...

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

برای دانلود 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

عنوان ژورنال:
  • Speech Communication

دوره 29  شماره 

صفحات  -

تاریخ انتشار 1999