Julie Carson-Berndsen
YOU?
Author Swipe
View article: Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuning
Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuning Open
While Large Language Models (LLMs) have made significant strides in replicating human-like abilities, there are concerns about a reduction in the linguistic diversity of their outputs. This results in the homogenization of viewpoints and p…
View article: Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction
Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correction Open
The integration of natural language processing (NLP) technologies into educational applications has shown promising results, particularly in the language learning domain. Recently, many spoken open-domain chatbots have been used as speakin…
View article: Investigating the Sensitivity of Automatic Speech Recognition Systems to Phonetic Variation in L2 Englishes
Investigating the Sensitivity of Automatic Speech Recognition Systems to Phonetic Variation in L2 Englishes Open
Automatic Speech Recognition (ASR) systems exhibit the best performance on speech that is similar to that on which it was trained. As such, underrepresented varieties including regional dialects, minority-speakers, and low-resource languag…
View article: Investigating Phoneme Similarity with Artificially Accented Speech
Investigating Phoneme Similarity with Artificially Accented Speech Open
While the deep learning revolution has led to significant performance improvements in speech recognition, accented speech remains a challenge. Current approaches to this challenge typically do not seek to understand and provide explanation…
View article: I already said that! Degenerating redundant questions in open-domain dialogue systems.
I already said that! Degenerating redundant questions in open-domain dialogue systems. Open
Neural text generation models have achieved remarkable success in carrying on short open-domain conversations. However, their performance degrades significantly in the long term, especially in their ability to ask coherent questions. A sig…
View article: Unsupervised domain adaptation for speech recognition with unsupervised error correction
Unsupervised domain adaptation for speech recognition with unsupervised error correction Open
The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption, ai…
View article: Sign2Speech: A Novel Sign Language to Speech Synthesis Pipeline
Sign2Speech: A Novel Sign Language to Speech Synthesis Pipeline Open
The lack of assistive Sign Language technologies for members of the Deaf community has impeded their access to public information, and curtailed their civil rights and social inclusion. In this paper, we introduce a novel proof-of-concept …
View article: Domain-Informed Probing of wav2vec 2.0 Embeddings for Phonetic Features
Domain-Informed Probing of wav2vec 2.0 Embeddings for Phonetic Features Open
In recent years large transformer model architectures have become available which provide a novel means of generating high-quality vector representations of speech audio. These transformers make use of an attention mechanism to generate re…
View article: The Influence of Regional Pronunciation Variation on Children’s Spelling and the Potential Benefits of Accent Adapted Spellcheckers
The Influence of Regional Pronunciation Variation on Children’s Spelling and the Potential Benefits of Accent Adapted Spellcheckers Open
A child who is unfamiliar with the correct spelling of a word often employs a “sound it out” approach: breaking the word down into its constituent sounds and then choosing letters to represent the identified sounds. This often results in a…
View article: Towards multilingual articulatory feature recognition with Support Vector Machines
Towards multilingual articulatory feature recognition with Support Vector Machines Open
We present experiments on mono-lingual and cross-lingual articulatory feature recognition for English and German speech data. Our goal is to investigate to what extent it is possible to derive and reuse articulatory feature recognizers, wh…
View article: The Effect of Phoneme Distribution on Perceptual Similarity in English
The Effect of Phoneme Distribution on Perceptual Similarity in English Open
The 20th Annual Conference of the International Speech Communication Association (Interspeech 2019), Graz, Austria, 15-19 September 2019
View article: Emotional response language education: a first ‘in-the-wild’ evaluation
Emotional response language education: a first ‘in-the-wild’ evaluation Open
The 20th International CALL Research Conference, The Education University of Hong Kong, Hong Kong, 10-12 July 2019