Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 6 of 6 for “"multilingual speech"”.

  1. Improving multilingual speech recognition systems

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms

    uiuc Repository record for Improving multilingual speech recognition systems (opens in a new tab)

  2. Transfer Learning For Spoken Language Processing

    … domain adaptation in the context of Automatic Speech Recognition (ASR) and Cross-Lingual Learning in Automatic Speech Translation (AST). The first part of the thesis develops an algorithm for unsupervised domain adaptation of End-to-End ASR models. In recent years, ASR performance has improved …

    mit Repository record for Transfer Learning For Spoken Language Processing (opens in a new tab)

  3. PLUTO : a preprocessor for multilingual spoken language generation

    … to simplify the development of such grammars in multilingual speech-based applications.

    mit Repository record for PLUTO : a preprocessor for multilingual spoken language generation (opens in a new tab)

  4. Speech Foundation Models for Audio Processing

    … shaped the development of natural language and speech technologies. Foundation speech models such as Whisper have shown strong performance across a variety of audio processing tasks, including automatic speech recognition (ASR) and speech translation. Unlike traditional systems that require …

    cambridge Repository record for Speech Foundation Models for Audio Processing (opens in a new tab)

  5. Können Hörende eine Stimme identifizieren, die in zwei verschiedenen L1 spricht?

    In dieser Studie wurde untersucht, ob Hörende dieselbe Stimme in zwei unterschiedlichen Erstsprachen (Deutsch, Japanisch) identifizieren können und welche Faktoren diese Leistung beeinflussen. Sprachproben von sechs bilingualen Sprecherinnen in gelesener und spontaner Sprache wurden aufgenommen und …

    humboldt-diss Repository record for Können Hörende eine Stimme identifizieren, die in zwei verschiedenen L1 spricht? (opens in a new tab)

  6. Multilingual Language Acquisition in Arabic-English Speaking Families: The Role of Parent Sex and Parent Education in Caregiver Report of Children’s Language Skills

    … exclusively reserved for reading and writing. Multilingual Arabic speakers are among the fastest growing language communities in the United States (US), yet very little is known about language development in Arabic-English speaking children, leading to critical knowledge gaps in language …

    ku Repository record for Multilingual Language Acquisition in Arabic-English Speaking Families: The Role of Parent Sex and Parent Education in Caregiver Report of Children’s Language Skills (opens in a new tab)