Related papers: An interview with Bernard Teissier
The year 2024 marks two anniversaries: The 70th anniversary of CERN and the 50th anniversary of the $J/\Psi$ discovery. At this occasion I have been asked to give review talks on the significance of these anniversaries. This article is an…
This paper introduces Timers and Such, a new open source dataset of spoken English commands for common voice control use cases involving numbers. We describe the gap in existing spoken language understanding datasets that Timers and Such…
Structured interviews are used in many settings, importantly in market research on topics such as brand perception, customer habits, or preferences, which are critical to product development, marketing, and e-commerce at large. Such…
In this paper, we explore different ways of training a model for handwritten text recognition when multiple imperfect or noisy transcriptions are available. We consider various training configurations, such as selecting a single…
Reversible interactions model different scenarios, like biochemical systems and human as well as automatic negotiations. We abstract interactions via multiparty sessions enriched with named checkpoints. Computations can either go forward or…
Introductory lectures on Extra Dimensions delivered at TASI 2004. The emphasis is on basic mechanisms rather than specific models.
The is the English version of the text of the talk at S\'eminaire Bourbaki on February 16, 2016
We present here the proceedings of the 5th seminar on emerging infectious diseases (EIDs), held in Paris on March 22nd, 2016, with seven priority proposals that can be outlined as follows:$\bullet$Encourage research on the prediction,…
The Teissier distribution, originally proposed by Teissier [31], was designed to model mortality due to aging in domestic animals. More recently, Krishna et al. [19] introduced the Unit Teissier (UT) distribution on the interval (0, 1)…
We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of…
We respond to some of the points made by Bennet and Blanck (2022) concerning a previous publication of ours (2021).
We describe a set of bilingual English--French and English--German parallel corpora in which the direction of translation is accurately and reliably annotated. The corpora are diverse, consisting of parliamentary proceedings, literary…
These are the notes on two-dimensional conformal field theory, based on a lecture course for graduate math students, given by P.M. in fall 2022 at the University of Notre Dame. These notes are intended to be substantially reworked and…
Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…
These notes are an account of a series of lectures given at the Les Houches Summer School "Active Matter and Non-equilibrium Statistical Physics" during August and September 2018. The lectures can be viewed online at…
This volume contains the proceedings of the 17th International Workshop on Expressiveness in Concurrency (EXPRESS'10), which took place on 30th August 2010 in Paris, co-located with CONCUR'10. The EXPRESS workshop series aim at bringing…
Human feedback data is a critical component in developing language models. However, collecting this feedback is costly and ultimately not scalable. Inspired by the way human interlocutors provide spontaneous unsolicited feedback to each…
Memorizing and utilizing speakers' personas is a common practice for response generation in long-term conversations. Yet, human-authored datasets often provide uninformative persona sentences that hinder response quality. This paper…
This is a slightly revised version of the Presidential address (General) delivered at the 84th Annual Conference of the Indian Mathematical Society held at Jammu, India during November 2018.
We introduce SPGISpeech 2.0, a dataset suitable for speaker-tagged transcription in the financial domain. SPGISpeech 2.0 improves the diversity of applicable modeling tasks while maintaining the core characteristic of the original…