Research on Architectures for Integrated Speech/Language Systems in Verbmobil [PDF]
, 1996 The German joint research project Verbmobil (VM) aims at the development of a speech to speech translation system. This paper reports on research done in our group which belongs to Verbmobil's subproject on system architectures (TP15).
Görz, Günther +3 more
core +5 more sources
LoRA-INT8 Whisper: A Low-Cost Cantonese Speech Recognition Framework for Edge Devices
SensorsTo address the triple bottlenecks of data scarcity, oversized models, and slow inference that hinder Cantonese automatic speech recognition (ASR) in low-resource and edge-deployment settings, this study proposes a cost-effective Cantonese ASR system ...
Lusheng Zhang, Shie Wu, Zhongxun Wang
doaj +1 more source
Grammatical Morphology in School-Age Children With and Without Language Impairment: A Discriminant Function Analysis [PDF]
, 2011 Purpose: The purpose of this study was to test Bedore and Leonard\u27s (1998) proposal that a verb morpheme composite may hold promise as a clinical marker for specific language impairment (SLI) in English speakers and serve as an accurate basis for the ...
Gorman, Brenda K. +2 more
core +2 more sources
FICTIVE CHANGE IN BRAZILIAN CORPUS OF SPONTANEOUS SPEECH
Gragoatá, 2016 This work investigates fictive change occurrences in spontaneous speech corpus of Brazilian Portuguese (BP) as The room got bigger after removing the furniture (O quarto ficou muito maior depois que retiraram os móveis), in which a change expressed by ...
Luiz Fernando Matos Rocha +2 more
doaj
Narrative in adolescent specific language impairment (SLI): a comparison with peers across two different narrative genres [PDF]
, 2007 Background: Narrative may provide a useful way in which to assess the language ability of adolescents with specific language impairment and may be more ecologically valid than standardized tests.
Botting, N. +2 more
core +1 more source
Radio Oranje: Enhanced Access to a Historical Spoken Word Collection [PDF]
, 2007 Access to historical audio collections is typically very restricted:\ud content is often only available on physical (analog) media and the\ud metadata is usually limited to keywords, giving access at the level\ud of relatively large fragments, e.g., an ...
Heeren, Willemijn +3 more
core +1 more source
The Effects of Altered Auditory Feedback (AAF) on Fluency in Adults Who Stutter: A Systematic Review [PDF]
, 2019 Background and Objectives: Stuttering affects 70 million people worldwide, which is about 1% of the population. Altered auditory feedback (AAF) is a process by which an individual’s auditory speech signal is electronically changed to temporarily increase
Kiley, Sullivan J +2 more
core +1 more source
Using term clouds to represent segment-level semantic content of podcasts [PDF]
, 2008 Spoken audio, like any time-continuous medium, is notoriously difficult to browse or skim without support of an interface providing semantically annotated jump points to signal the user where to listen in.
Besser, Jana +6 more
core
Evaluation of spoken document retrieval for historic speech collections [PDF]
, 2008 The re-use of spoken word audio collections maintained by audiovisual archives is severely hindered by their generally limited access. The CHoral project, which is part of the CATCH program funded by the Dutch Research Council, aims to provide users of ...
Heeren, W. +4 more
core +1 more source
Challenging Neural Dialogue Models with Natural Data: Memory Networks Fail on Incremental Phenomena
, 2017 Natural, spontaneous dialogue proceeds incrementally on a word-by-word basis; and it contains many sorts of disfluency such as mid-utterance/sentence hesitations, interruptions, and self-corrections.
Eshghi, Arash +2 more
core +1 more source