Disfluency processing for cascaded speech translation involving English and Indian languages.

Disfluencies are common in spontaneous speech and can significantly impact the accuracy of automatic speech translation when a spoken text is used as is as input. We address this issue by implementing two different approaches in our cascaded speech translation system. First, we identify and process...

Full description

Bibliographic Details
Published in:Language Resources & Evaluation Vol. 59; no. 3; pp. 2653 - 2687
Main Authors: Mujadia, Vandan, Mishra, Pruthwik, Sharma, Dipti Misra
Format: Conference Paper/Materials
Published: Springer Nature Sep2025
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=186909077&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 186909077
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Sep2025
      vid: 59
      iid: 3
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        186909077
        10.1007/s10579-025-09818-3
      ppf: 2653
      ppct: 34
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 1.4MB
      tig:
        atl: Disfluency processing for cascaded speech translation involving English and Indian languages.
      aug:
        au:
          Mujadia, Vandan
          Mishra, Pruthwik
          Sharma, Dipti Misra
        affil: https://ror.org/00qryer39 Language Technologies Research Centre (LTRC), International Institute of Information Technology, 500032, Hyderabad, Telangana, India
      su:
        Automatic speech recognition
        Speech processing systems
        Corpora
        Machine translating
        Language & languages
        Translating & interpreting
        English language
      sug:
        subj:
          Automatic speech recognition
          Speech processing systems
          Corpora
          Machine translating
          Language & languages
          Translating & interpreting
          English language
      keyword:
        Communication and Culture Linguistics Information and Computing Sciences Artificial Intelligence and Image Processing Psychology and Cognitive Sciences Cognitive Sciences
        Disfluency for English to Indian language speech translation
        Disfluency processing
        Indian languages
        Language
        Speech translation
      ab: Disfluencies are common in spontaneous speech and can significantly impact the accuracy of automatic speech translation when a spoken text is used as is as input. We address this issue by implementing two different approaches in our cascaded speech translation system. First, we identify and process the disfluencies in the spoken text before feeding the transcript to machine translation. Second, we train the machine translation system to be aware of disfluencies, enabling it to handle disfluencies and accurately translate both fluent and disfluent texts. We observe improvements of up to + 2.39 BLEU points (or + 0.90 COMET points) in speech translation from English to Bangla, Gujarati, Hindi, Kannada, Malayalam, Marathi, Tamil and Telugu languages when the state-of-the-art disfluency identifier system is used to preprocess disfluencies on our speech translation testset. We employed a synthetic disfluency corpora creation algorithm to augment existing machine translation parallel corpora involving English and 11 Indian languages. The machine translation system trained on it can handle the disfluencies inherent in spoken text and produce accurate translations. When applied to our speech translation test-set, this approach results in improvements of up to + 1.90 BLEU points (or + 0.60 COMET points) for translations from English to Bangla, Gujarati, Hindi, Kannada, Malayalam, Marathi, Tamil, and Telugu on our developed speech translation test-set.
      pubtype: Academic Journal
      doctype: Conference Paper/Materials
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Language Resources & Evaluation is a copyright of Springer, 2025. All Rights Reserved.
      item: Language Resources & Evaluation
      holder: Springer Nature
      dt:
        @attributes:
          year: 2025
    holdings:
      @attributes:
        islocal: N