Maria Teleki
@mariateleki.bsky.social
Howdy 🤠 | PhD in CS @ Texas A&M
🎙️ #speech #AI #NLP #recsys
🐶 Apollo’s human | 🛶 Rowing to 1M meters
🌐 https://mariateleki.github.io/
🎙️ #speech #AI #NLP #recsys
🐶 Apollo’s human | 🛶 Rowing to 1M meters
🌐 https://mariateleki.github.io/
Pinned
Maria Teleki
@mariateleki.bsky.social
· Sep 25
🌟 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.
🤔 Traditional F1 scores hide why disfluency removal models succeed or fail.
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. 📊
buff.ly
November 11, 2025 at 4:38 PM
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
Our survey shows they struggle with:
⚠️ Long-term coherence
⚠️ Controllability
📚 Paper: mariateleki.github.io/pdf/A_Survey...
#StoryGeneration #GenerativeAI #NLP
November 8, 2025 at 7:15 PM
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
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
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
November 3, 2025 at 6:02 PM
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
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
#AcademicMentoring #PhDLife
November 1, 2025 at 6:15 PM
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
#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
That’s why I build evaluation frameworks for speech & conversational AI — so we can stress-test systems against real-world variability.
#AIResearch #Evaluation #SpeechProcessing
October 25, 2025 at 6:15 PM
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
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
Because speech ≠ text.
🎙️ People pause, restart, self-correct
🌎 Background noise & accents vary
💬 Context shifts across domains
October 20, 2025 at 6:29 PM
Why “speech-first” AI?
Because speech ≠ text.
🎙️ People pause, restart, self-correct
🌎 Background noise & accents vary
💬 Context shifts across domains
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
“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
October 18, 2025 at 6:15 PM
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
“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?
October 15, 2025 at 5:05 PM
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
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
October 11, 2025 at 6:15 PM
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
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
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
October 4, 2025 at 6:15 PM
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
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!)
📚 Covers: controllability, coherence, and creativity
🧩 Discusses: evaluation challenges
🌍 Highlights: hybrid symbolic–neural approaches
💻 Includes: an open resource list (PRs welcome!)
September 27, 2025 at 6:15 PM
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!)
📚 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!
September 25, 2025 at 5:40 PM
🚀 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.
🤔 Traditional F1 scores hide why disfluency removal models succeed or fail.
September 25, 2025 at 5:22 PM
🌟 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.
🤔 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”).
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”).
September 24, 2025 at 5:06 PM
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”).
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.
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.
September 21, 2025 at 7:00 PM
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.
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. 🧵
In our INTERSPEECH 2025 paper, we studied whole-word substitution errors. 🧵
September 20, 2025 at 6:15 PM
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. 🧵
In our INTERSPEECH 2025 paper, we studied whole-word substitution errors. 🧵
Reposted by Maria Teleki
I can confirm that the authors of this website are heroes and we should all pay them money: poloclub.github.io/transformer-...
September 18, 2025 at 5:24 PM
I can confirm that the authors of this website are heroes and we should all pay them money: poloclub.github.io/transformer-...
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”). 🧵
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”). 🧵
September 13, 2025 at 6:15 PM
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”). 🧵
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
Now that school is starting for lots of folks, it's time for a new release of Speech and Language Processing! Jim and I added all sorts of material for the August 2025 release! With slides to match! Check it out here: web.stanford.edu/~jurafsky/sl...
Speech and Language Processing
Speech and Language Processing
web.stanford.edu
August 24, 2025 at 7:28 PM
Now that school is starting for lots of folks, it's time for a new release of Speech and Language Processing! Jim and I added all sorts of material for the August 2025 release! With slides to match! Check it out here: web.stanford.edu/~jurafsky/sl...
Excited to share our paper A Survey on LLMs for Story Generation! 🎉
We’re also releasing a community resource on GitHub — please feel free to send a pull request as new systems come out.
Paper: tinyurl.com/3jmdkx72
Github: tinyurl.com/2hmrkvrt
#NLP #LLMs #EMNLP2025
We’re also releasing a community resource on GitHub — please feel free to send a pull request as new systems come out.
Paper: tinyurl.com/3jmdkx72
Github: tinyurl.com/2hmrkvrt
#NLP #LLMs #EMNLP2025
September 6, 2025 at 6:15 PM
Excited to share our paper A Survey on LLMs for Story Generation! 🎉
We’re also releasing a community resource on GitHub — please feel free to send a pull request as new systems come out.
Paper: tinyurl.com/3jmdkx72
Github: tinyurl.com/2hmrkvrt
#NLP #LLMs #EMNLP2025
We’re also releasing a community resource on GitHub — please feel free to send a pull request as new systems come out.
Paper: tinyurl.com/3jmdkx72
Github: tinyurl.com/2hmrkvrt
#NLP #LLMs #EMNLP2025