Maria Teleki
Howdy 🤠 | PhD in CS @ Texas A&M
🎙️ Speech AI/RecSys
🐶 Apollo’s human
🌐 mariateleki.github.io
- 🗣️ People don’t speak in clean sentences. They pause, restart, hedge, revise, and change direction mid-thought. 𝗠𝘆 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝘀𝘁𝗮𝗿𝘁𝘀 𝗳𝗿𝗼𝗺 𝗮 𝘀𝗶𝗺𝗽𝗹𝗲 𝗽𝗿𝗲𝗺𝗶𝘀𝗲: 𝗧𝗵𝗲𝘀𝗲 “𝗺𝗲𝘀𝘀𝘆” 𝗽𝗵𝗲𝗻𝗼𝗺𝗲𝗻𝗮 𝗮𝗿𝗲 𝗻𝗼𝘁 𝗻𝗼𝗶𝘀𝗲, 𝘁𝗵𝗲𝘆 𝗮𝗿𝗲 𝗳𝘂𝗻𝗱𝗮𝗺𝗲𝗻𝘁𝗮𝗹 𝗳𝗲𝗮𝘁𝘂𝗿𝗲𝘀 𝗼𝗳 𝗵𝘂𝗺𝗮𝗻 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝗰𝗮𝘁𝗶𝗼𝗻.
- We evaluated how prompt recommender systems (PRS) 𝗰𝗵𝗮𝗻𝗴𝗲 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 with AI systems -- 📊 Study design: • 2×2 fully within-subjects • Creative vs. Academic writing • PromptHelper 𝗢𝗡 vs. 𝗢𝗙𝗙
- In our new work, 🎶 CHOIR: Collaborative Harmonization fOr Inference Robustness, we show that different LLM personas often get different benchmark questions right! CHOIR leverages this diversity to boost performance across benchmarks. 📊
- LLMs can write — but can they tell stories? Our survey shows they struggle with: ⚠️ Long-term coherence ⚠️ Controllability 📚 Paper: mariateleki.github.io/pdf/A_Survey... #StoryGeneration #GenerativeAI #NLP
- Disfluencies aren’t just noise — they’re part of how we speak. In our #INTERSPEECH2024 paper, we looked at how Google ASR vs WhisperX handle messy, real-world podcasts (82k+ episodes!): 🎙️ WhisperX → better with “uh/um” 📝 Google ASR → better with self-corrections
- Highlight of my PhD → mentoring students. It's literally just the most fun to brainstorm with them each week and watch them learn and grow 🌱 #AcademicMentoring #PhDLife
- We can’t fix what we don’t measure. That’s why I build evaluation frameworks for speech & conversational AI — so we can stress-test systems against real-world variability. #AIResearch #Evaluation #SpeechProcessing
- Why “speech-first” AI? Because speech ≠ text. 🎙️ People pause, restart, self-correct 🌎 Background noise & accents vary 💬 Context shifts across domains
- What happens when you say: “I want a horror -- comedy -- movie”? 🎥 That slip-of-the-tongue can confuse recommender systems. Our INTERSPEECH 2025 paper shows some LLMs handle it better than others. 📄 mariateleki.github.io/pdf/HorrorCo... #INTERSPEECH2025 #ConversationalAI #RecSys
- Last year at INTERSPEECH 2024, we explored a question that remains relevant: how do ASR systems handle disfluencies in real-world speech?
- Stories shape how we think and connect. 📖 But can AI tell a good story? Our Survey on LLMs for Story Generation (EMNLP Findings 2025) explores: ✨ Coherence 🎛️ Controllability 🎨 Creativity ⚖️ Authenticity 📄 mariateleki.github.io/pdf/A_Survey... #StoryGeneration #GenerativeAI
- Speech isn’t perfect. We restart, repeat, and slip. For AI, those little disfluencies can cause big problems. That’s why my research builds methods to make spoken language systems more robust. #SpeechProcessing #ConversationalAI #NLP #AI
- Back in August, we shared our Survey on LLMs for Story Generation (EMNLP Findings 2025). 📚 Covers: controllability, coherence, and creativity 🧩 Discusses: evaluation challenges 🌍 Highlights: hybrid symbolic–neural approaches 💻 Includes: an open resource list (PRs welcome!)
- 🚀 New on arXiv: We introduce DRES, the disfluency removal evaluation suite!
- 🌟 New on arXiv — we introduce Z-Scores: A Metric for Linguistically Assessing Disfluency Removal 📊🧠 🤔 Traditional F1 scores hide why disfluency removal models succeed or fail.
- Speech is messy — and so are recommender systems when they face speech errors. In our INTERSPEECH 2025 paper, we introduced Syn-WSSE, a psycholinguistically grounded framework for simulating whole-word substitution errors in conversational recommenders (e.g., “I want a horror—comedy movie”).
- Messy, real-world speech ≠ clean transcripts. In our #INTERSPEECH2024 paper, we compared Google ASR vs WhisperX on 82k+ podcasts 🎙️ 🌱 WhisperX → better with accurately transcribing “uh/um” 🌱 Google ASR → better with accurately transcribing edited nodes 🌱 Which to use? Depends on your data.
- Speech isn’t always clean — we make slips-of-the-tongue all the time. But what happens when those disfluencies hit conversational recommender systems? In our INTERSPEECH 2025 paper, we studied whole-word substitution errors. 🧵
- Reposted by Maria Teleki[Not loaded yet]
- When we think about bias in AI, we often imagine stereotypes like “doctor/nurse.” But bias also hides in how we speak. Our ICWSM 2025 paper showed that men’s discourse markers (“going,” “well”) are treated as more “stable” in LLM embeddings than women’s (“like,” “really”). 🧵
- Reposted by Maria Teleki[Not loaded yet]
