74 citations · 78 across the 7 of their papers we have counts for
8 papers
PEDBench: Can Speech Models Detect Phonetic Errors?
Zhonghao Shi, Zackary Rackauckas, Jasmine Yip +9
Phonetic error detection (PED) aims to identify phoneme-level substitutions, deletions, and insertions and is essential for educational and clinical speech assessment and intervent…
A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges
Wen Liang, Li Siyan, Zackary Rackauckas +1
Automated coaching for oral presentations sits at the intersection of computer-assisted pronunciation training (CAPT), prosody modeling, and speech synthesis, yet no prior work has…
Re:Member: Emotional Question Generation from Personal Memories
Zackary Rackauckas, Nobuaki Minematsu, Julia Hirschberg
We present Re:Member, a system that explores how emotionally expressive, memory-grounded interaction can support more engaging second language (L2) learning. By drawing on users' p…
Animating Language Practice: Engagement with Stylized Conversational Agents in Japanese Learning
Zackary Rackauckas, Julia Hirschberg
We explore Jouzu, a Japanese language learning application that integrates large language models with anime-inspired conversational agents. Designed to address challenges learners…
VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering
Zackary Rackauckas, Julia Hirschberg
We introduce VoxRAG, a modular speech-to-speech retrieval-augmented generation system that bypasses transcription to retrieve semantically relevant audio segments directly from spo…
Comparative Evaluation of Expressive Japanese Character Text-to-Speech with VITS and Style-BERT-VITS2
Zackary Rackauckas, Julia Hirschberg
Synthesizing expressive Japanese character speech poses unique challenges due to pitch-accent sensitivity and stylistic variability. This paper empirically evaluates two open-sourc…
Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework
Zackary Rackauckas, Arthur Câmara, Jakub Zavrel
Challenges in the automated evaluation of Retrieval-Augmented Generation (RAG) Question-Answering (QA) systems include hallucination problems in domain-specific knowledge and the l…
RAG-Fusion: a New Take on Retrieval-Augmented Generation
Zackary Rackauckas
Infineon has identified a need for engineers, account managers, and customers to rapidly obtain product information. This problem is traditionally addressed with retrieval-augmente…