BEGIN:VCALENDAR VERSION:2.0 PRODID:-//128.220.36.25//NONSGML kigkonsult.se iCalcreator 2.26.9// CALSCALE:GREGORIAN METHOD:PUBLISH X-FROM-URL:https://www.clsp.jhu.edu X-WR-TIMEZONE:America/New_York BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:STANDARD DTSTART:20231105T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RDATE:20241103T020000 TZNAME:EST END:STANDARD BEGIN:DAYLIGHT DTSTART:20240310T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RDATE:20250309T020000 TZNAME:EDT END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:ai1ec-20115@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:
Abstract
\nData science in small medi cal datasets usually means doing precision guesswork on unreliable data pr ovided by those with high expectations. The first part of this talk will f ocus on issues that data scientists and engineers have to address when wor king with this kind of data (e.g. unreliable labels\, the effect of confou nding factors\, necessity of clinical interpretability\, difficulties with fusing more data sets). The second part of the talk will include some rea l examples of this kind of data science in the field of neurology (predict ion of motor deficits in Parkinson’s disease based on acoustic analysis of speech\, diagnosis of Parkinson’s disease dysgraphia utilising online han dwriting\, exploring the Mozart effect in epilepsy based on the music info rmation retrieval) and psychology (assessment of graphomotor disabilities in children with developmental dysgraphia).
\nBiography
\nAbstract
\nAdversarial atta cks deceive neural network systems by adding carefully crafted perturbatio ns to benign signals. Being almost imperceptible to humans\, these attacks pose a severe security threat to the state-of-the-art speech and speaker recognition systems\, making it vital to propose countermeasures against t hem. In this talk\, we focus on 1) classification of a given adversarial a ttack into attack algorithm type\, threat model type\, and signal-to-adver sarial-noise ratios\, 2) developing a novel speech denoising solution to f urther improve the classification performance.
\nO ur proposed approach uses an x-vector network as a signature extractor to get embeddings\, which we call signatures. These signatures contain inform ation about the attack and can help classify different attack algorithms\, threat models\, and signal-to-adversarial-noise ratios. We demonstrate th e transferability of such signatures to other tasks. In particular\, a sig nature extractor trained to classify attacks against speaker identificatio n can also be used to classify attacks against speaker verification and sp eech recognition. We also show that signatures can be used to detect unkno wn attacks i.e. attacks not included during training. Lastly\, we propose to improve the signature extractor by making the job of the signature ext ractor easier by removing the clean signal from the adversarial example (w hich consists of clean signal+perturbation). We train our signature extrac tor using adversarial perturbation. At inference time\, we use a time-doma in denoiser to obtain adversarial perturbation from adversarial examples. Using our improved approach\, we show that common attacks in the literatur e (Fast Gradient Sign Method (FGSM)\, Projected Gradient Descent (PGD)\, C arlini-Wagner (CW) ) can be classified with accuracy as high as 96%. We al so detect unknown attacks with an equal error rate (EER) of about 9%\, whi ch is very promising.
DTSTART;TZID=America/New_York:20220304T120000 DTEND;TZID=America/New_York:20220304T131500 LOCATION:Ames Hall 234 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Student Seminar – Sonal Joshi “Classify and Detect Adversarial Atta cks Against Speaker and Speech Recognition Systems” URL:https://www.clsp.jhu.edu/events/student-seminar-sonal-joshi/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,Joshi\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-21615@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Student Seminars CONTACT: DESCRIPTION:Abstract
\nDTSTART;TZID=America/New_York:20220311T120000 DTEND;TZID=America/New_York:20220311T131500 LOCATION:Virtual Seminar SEQUENCE:0 SUMMARY:Student Seminar – Anton Belyy “Systems for Human-AI Cooperation on Collecting Semantic Annotations” URL:https://www.clsp.jhu.edu/events/student-seminar-anton-belyy-systems-for -human-ai-cooperation-on-collecting-semantic-annotations/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,Belyy\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-21621@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:
Abstract
\nSystems that support expre ssive\, situated natural language interactions are essential for expanding access to complex computing systems\, such as robots and databases\, to n on-experts. Reasoning and learning in such natural language interactions i s a challenging open problem. For example\, resolving sentence meaning req uires reasoning not only about word meaning\, but also about the interacti on context\, including the history of the interaction and the situated env ironment. In addition\, the sequential dynamics that arise between user an d system in and across interactions make learning from static data\, i.e.\ , supervised data\, both challenging and ineffective. However\, these same interaction dynamics result in ample opportunities for learning from impl icit and explicit feedback that arises naturally in the interaction. This lays the foundation for systems that continually learn\, improve\, and ada pt their language use through interaction\, without additional annotation effort. In this talk\, I will focus on these challenges and opportunities. First\, I will describe our work on modeling dependencies between languag e meaning and interaction context when mapping natural language in interac tion to executable code. In the second part of the talk\, I will describe our work on language understanding and generation in collaborative interac tions\, focusing on continual learning from explicit and implicit user fee dback.
\nBiography
\nAlane Suhr is a PhD Cand idate in the Department of Computer Science at Cornell University\, advis ed by Yoav Artzi. Her research spans natural language processing\, machine learning\, and computer vision\, with a focus on building systems that pa rticipate and continually learn in situated natural language interactions with human users. Alane’s work has been recognized by paper awards at ACL and NAACL\, and has been supported by fellowships and grants\, including a n NSF Graduate Research Fellowship\, a Facebook PhD Fellowship\, and resea rch awards from AI2\, ParlAI\, and AWS. Alane has also co-organized multip le workshops and tutorials appearing at NeurIPS\, EMNLP\, NAACL\, and ACL. Previously\, Alane received a BS in Computer Science and Engineering as a n Eminence Fellow at the Ohio State University.
DTSTART;TZID=America/New_York:20220314T120000 DTEND;TZID=America/New_York:20220314T131500 LOCATION:Virtual Seminar SEQUENCE:0 SUMMARY:Alane Suhr (Cornell University) “Reasoning and Learning in Interact ive Natural Language Systems” URL:https://www.clsp.jhu.edu/events/alane-suhr-cornell-university-reasoning -and-learning-in-interactive-natural-language-systems/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,March\,Suhr END:VEVENT BEGIN:VEVENT UID:ai1ec-21616@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Student Seminars CONTACT: DESCRIPTION:Abstract
\nSocial media allows resear chers to track societal and cultural changes over time based on language a nalysis tools. Many of these tools rely on statistical algorithms which ne ed to be tuned to specific types of language. Recent studies have shown th e absence of appropriate tuning\, specifically in the presence of semantic shift\, can hinder robustness of the underlying methods. However\, little is known about the practical effect this sensitivity may have on downstre am longitudinal analyses. We explore this gap in the literature through a timely case study: understanding shifts in depression during the course of the COVID-19 pandemic. We find that inclusion of only a small number of s emantically-unstable features can promote significant changes in longitudi nal estimates of our target outcome. At the same time\, we demonstrate tha t a recently-introduced method for measuring semantic shift may be used to proactively identify failure points of language-based models and\, in tur n\, improve predictive generalization.
DTSTART;TZID=America/New_York:20220318T120000 DTEND;TZID=America/New_York:20220318T131500 LOCATION:Ames Hall 234 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Student Seminar – Keith Harrigian “The Problem of Semantic Shift in Longitudinal Monitoring of Social Media” URL:https://www.clsp.jhu.edu/events/student-seminar-keith-harrigian-the-pro blem-of-semantic-shift-in-longitudinal-monitoring-of-social-media/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,Harrigian\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-21497@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nWhile the “deep learning t sunami” continues to define the state of the art in speech and language pr ocessing\, finite-state transducer grammars developed by linguists and eng ineers are still widely used in industrial\, highly-multilingual settings\ , particularly for symbolic\, “front-end” speech applications. In this tal k\, I will first briefly review the current state of the OpenFst and OpenG rm finite-state transducer libraries. I then review two “late-breaking” al gorithms found in these libraries. The first is a heuristic but highly-eff ective general-purpose optimization routine for weighted transducers. The second is an algorithm for computing the single shortest string of non-det erministic weighted acceptors which lack certain properties required by cl assic shortest-path algorithms. I will then illustrate how the OpenGrm too ls can be used to induce a finite-state string-to-string transduction mode l known as a pair n-gram model. This model has been applied to grapheme-to -phoneme conversion\, loanword detection\, abbreviation expansion\, and ba ck-transliteration\, among other tasks.
\nBiography
\nKyle Gorman is an assistant professor of linguistics at the Gradu ate Center\, City University of New York\, and director of the master’s pr ogram in computational linguistics\; he is also a software engineer in the speech and language algorithms group at Google. With Richard Sproat\, he is the coauthor of Finite-State Text Processing (Morgan & Claypool\ , 2021) and the creator of Pynini\, a finite-state text processing library for Python. He has also published on statistical methods for comparing co mputational models\, text normalization\, grapheme-to-phoneme conversion\, and morphological analysis\, as well as many topics in linguistic theory.
DTSTART;TZID=America/New_York:20220401T120000 DTEND;TZID=America/New_York:20220401T131500 LOCATION:Ames Hall 234 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Kyle Gorman (City University of New York) ” Weighted Finite-State T ransducers: The Later Years” URL:https://www.clsp.jhu.edu/events/kyle-gorman-city-university-of-new-york -weighted-finite-state-transducers-the-later-years/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,Gorman\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-22400@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nModern learning architectures for natural language processing have been very suc cessful in incorporating a huge amount of texts into their parameters. How ever\, by and large\, such models store and use knowledge in distributed a nd decentralized ways. This proves unreliable and makes the models ill-sui ted for knowledge-intensive tasks that require reasoning over factual info rmation in linguistic expressions. In this talk\, I will give a few examp les of exploring alternative architectures to tackle those challenges. In particular\, we can improve the performance of such (language) models by r epresenting\, storing and accessing knowledge in a dedicated memory compon ent.
\nThis talk is based on several joint works with Yury Zemlyanskiy (Google Research)\, Michiel de Jong (USC and Google Research)\, William Cohen (Google Research and CMU) and our other collabo rators in Google Research.
\nBiography
\nFei is a research scientist at Google Research. Before that\, he was a Profess or of Computer Science at University of Southern California. His primary r esearch interests are machine learning and its application to various AI p roblems: speech and language processing\, computer vision\, robotics and r ecently weather forecast and climate modeling. He has a PhD (2007) from Computer and Information Science from U. of Pennsylvania and B.Sc and M.Sc in Biomedical Engineering from Southeast University (Nanjing\, China).
DTSTART;TZID=America/New_York:20221024T120000 DTEND;TZID=America/New_York:20221024T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Fei Sha (University of Southern California) “Extracting Information from Text into Memory for Knowledge-Intensive Tasks” URL:https://www.clsp.jhu.edu/events/fei-sha-university-of-southern-californ ia/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2022\,October\,Sha END:VEVENT BEGIN:VEVENT UID:ai1ec-23320@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nSpeech communications repr esents a core domain for education\, team problem solving\, social engagem ent\, and business interactions. The ability for Speech Technology to extr act layers of knowledge and assess engagement content represents the next generation of advanced speech solutions. Today\, the emergence of BIG DATA \, Machine Learning\, as well as voice enabled speech systems have require d the need for effective voice capture and automatic speech/speaker recogn ition. The ability to employ speech and language technology to assess huma n-to-human interactions offers new research paradigms having profound impa ct on assessing human interaction. In this talk\, we will focus on big dat a naturalistic audio processing relating to (i) child learning spaces\, an d (ii) the NASA APOLLO lunar missions. ML based technology advancements in clude automatic audio diarization\, speech recognition\, and speaker recog nition. Child-Teacher based assessment of conversational interactions are explored\, including keyword and “WH-word” (e.g.\, who\, what\, etc.). Dia rization processing solutions are applied to both classroom/learning space child speech\, as well as massive APOLLO data. CRSS-UTDallas is expanding our original Apollo-11 corpus\, resulting in a massive multi-track audio processing challenge to make available 150\,000hrs of Apollo mission data to be shared with science communities: (i) speech/language technology\, (i i) STEM/science and team-based researchers\, and (iii) education/historica l/archiving specialists. Our goals here are to provide resources which all ow to better understand how people work/learn collaboratively together. Fo r Apollo\, to accomplish one of mankind’s greatest scientific/technologica l challenges in the last century.
\nBiography
\nJohn H.L. Hansen\, received Ph.D. & M.S. degrees from Georgia Institute of Technology\, and B.S.E.E. from Rutgers Univ. He joined Univ. of Texas at Dallas (UTDallas) in 2005\, where he currently serves as Associate Dean for Research\, Prof. of ECE\, Distinguished Univ. Chair in Telecom. Engin eering\, and directs Center for Robust Speech Systems (CRSS). He is an ISC A Fellow\, IEEE Fellow\, and has served as Member and TC-Chair of IEEE Sig nal Proc. Society\, Speech & Language Proc. Tech. Comm.(SLTC)\, and Techni cal Advisor to U.S. Delegate for NATO (IST/TG-01). He served as ISCA Presi dent (2017-21)\, continues to serve on ISCA Board (2015-23) as Treasurer\, has supervised 99 PhD/MS thesis candidates (EE\,CE\,BME\,TE\,CS\,Ling.\,C og.Sci.\,Spch.Sci.\,Hear.Sci)\, was recipient of 2020 UT-Dallas Provost’s Award for Grad. PhD Research Mentoring\; author/co-author of 865 journal/c onference papers including 14 textbooks in the field of speech/language/he aring processing & technology including coauthor of textbook Discrete-Time Processing of Speech Signals\, (IEEE Press\, 2000)\, and lead author of t he report “The Impact of Speech Under ‘Stress’ on Military Speech Technolo gy\,” (NATO RTO-TR-10\, 2000). He served as Organizer\, Chair/Co-Chair/Tec h.Chair for ISCA INTERSPEECH-2022\, IEEE ICASSP-2010\, IEEE SLT-2014\, ISC A INTERSPEECH-2002\, and Tech. Chair for IEEE ICASSP-2024. He received the 2022 IEEE Signal Processing Society Leo Beranek MERITORIOUS SERVICE Award .
\nDTSTART;TZID=America/New_York:20230303T120000 DTEND;TZID=America/New_York:20230303T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:John Hansen (University of Texas at Dallas) “Challenges and Advance ments in Speaker Diarization & Recognition for Naturalistic Data Streams” URL:https://www.clsp.jhu.edu/events/john-hansen-university-of-texas-at-dall as/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2023\,Hansen\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-23439@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:
Abstract
\nAs data-based technologies proliferate\, it is increasingly important for researchers to be aware of their work’s wider impact. Concerns like navigating the IRB and figuring out copyright and licensing issues are still key\, but the current focus s hift to matters like inclusivity\, fairness\, and transparency and their i mpact on the research/development life cycle have added complexity to the research task. In this talk\, we will take a broad look at the various way s ethics intersects with natural language processing\, machine learning\, and artificial intelligence research and discuss strategies and resources for managing these concerns within the broader research framework.
\nBiography
\nDenise is responsible for the overall operation of LDC’s External Relations group which includes intellectual pr operty management\, licensing\, regulatory matters\, publications\, member ship and communications. Before joining LDC\, she practiced law for over 2 0 years in the areas of international trade\, intellectual property and co mmercial litigation. She has an A.B. in Political Science from Bryn Mawr C ollege and a Juris Doctor degree from the University of Miami School of La w.
DTSTART;TZID=America/New_York:20230310T120000 DTEND;TZID=America/New_York:20230310T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street SEQUENCE:0 SUMMARY:Denise DiPersio (Linguistic Data Consortium\, University of Pennsyl vania) “Data and Ethics: Where Does the Twain Meet?” URL:https://www.clsp.jhu.edu/events/denise-dipersio-linguistic-data-consort ium-university-of-pennsylvania-data-and-ethics-where-does-the-twain-meet/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2023\,DiPersio\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-23505@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nRecent advances in large pretrained language models have unlocked new exciting a pplications for Natural Language Generation for creative tasks\, such as l yrics or humour generation. In this talk we will discuss recent works by o ur team at Alexa AI and discuss current challenges: (1) Pun understanding and generation: We release new datasets for pun understanding and the nove l task of context-situated pun generation\, and demonstrate the value of o ur annotations for pun classification and generation tasks. (2) Song lyric generation: we design a hierarchical lyric generation framework that enab les us to generate pleasantly-singable lyrics without training on melody-l yric aligned data\, and show that our approach is competitive with strong baselines supervised on parallel data. (3) Create with Alexa: a multimodal story creation experience recently launched on Alexa devices\, which leve rages story text generation models in tandem with story visualization and background music generation models to produce multimodal stories for kids.
\nBiography
\nAlessandra Cervone is an Appli ed Scientist in the Natural Understanding team at Amazon Alexa AI. Alessan dra holds an MSc in Speech and Language Processing from University of Edin burgh and a PhD in CS from University of Trento (Italy). During her PhD\, Alessandra worked on computational models of coherence in open-domain dial ogue advised by Giuseppe Riccardi. In the first year of the PhD\, she was the team leader of one of the teams selected to compete in the first editi on of the Alexa Prize. More recently\, her research interests have been fo cused on natural language generation and its evaluation\, in particular in the context of creative AI applications.
\nDTSTART;TZID=America/New_York:20230317T120000 DTEND;TZID=America/New_York:20230317T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Alessandra Cervone (Amazon) “Controllable Text Generation for Creat ive Applications URL:https://www.clsp.jhu.edu/events/alexxandra-cervone-amazon/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2023\,Cervone\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-23555@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Student Seminars CONTACT: DESCRIPTION: DTSTART;TZID=America/New_York:20230327T120000 DTEND;TZID=America/New_York:20230327T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Student Seminar – Desh Raj URL:https://www.clsp.jhu.edu/events/student-seminar-desh-raj-2/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2023\,March\,Raj END:VEVENT BEGIN:VEVENT UID:ai1ec-23513@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:
Abstract
\nDespite many recent advanc es in automatic speech recognition (ASR)\, linguists and language communit ies engaged in language documentation projects continue to face the obstac le of the “transcription bottleneck”. Researchers in NLP typically do not distinguish between widely spoken languages that currently happen to have few training resources and endangered languages that will never have abund ant data. As a result\, we often fail to thoroughly explore when ASR is he lpful for language documentation\, what architectures work best for the so rts of languages that are in need of documentation\, and how data can be c ollected and organized to produce optimal results. In this talk I describe several projects that attempt to bridge the gap between the promise of AS R for language documentation and the reality of using this technology in r eal-world settings.
\nBiography
\nAbstract
\nMost machine translation s ystems operate on the sentence-level while humans write and translate with in a given context. Operating on individual sentences forces error-prone s entence segmentation into the machine translation pipeline. This limits th e upper-bound performance of these systems by creating noisy training bite xt. Further\, many grammatical features necessitate inter-sentential conte xt in order to translate which makes perfect sentence-level machine transl ation an impossible task. In this talk\, we will cover the inherent limits of sentence-level machine translation. Following this\, we will explore a key obstacle in the way of true context-aware machine translation—an abje ct lack of data. Finally\, we will cover recent work that provides (1) a new evaluation dataset that specifically addresses the translation of cont ext-dependent discourse phenomena and (2) reconstructed documents from lar ge-scale sentence-level bitext that can be used to improve performance whe n translating these types of phenomena.
DTSTART;TZID=America/New_York:20240304T120000 DTEND;TZID=America/New_York:20240304T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Rachel Wicks (JHU) “To Sentences and Beyond: Paving the Way for Con text-Aware Machine Translation” URL:https://www.clsp.jhu.edu/events/rachel-wicks-jhu/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2024\,March\,Wicks END:VEVENT BEGIN:VEVENT UID:ai1ec-24465@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nLarge Language Models (LLM s) have demonstrated remarkable capabilities across various domains. Howev er\, it is still very challenging to build highly-reliable applications wi th LLMs that support specialized use cases. LLMs trained on web data often excel at capturing general language patterns\, but they could struggle to support specialized domains and personalized user needs. Moreover\, LLMs can produce errors that are deceptively plausible\, making them potentiall y dangerous for high-trust scenarios. In this talk\, I will discuss some o f our recent efforts in addressing these challenges with data-efficient tu ning methods and a novel factuality evaluation framework. Specifically\, m y talk will focus on building multilingual applications\, one crucial use case often characterized by limited tuning and evaluation data.
\nBio
Xinyi(Cindy) Wang is a research scientist at Go ogle DeepMind working on Large Language Models(LLM) and its application to generative question-answering. She has worked on multilingual instruction -tuning for Gemini and multilingual generative models used in Google searc h. Before Google DeepMind\, Cindy Wang obtained her PhD degree in Language Technologies at Carnegie Mellon University. During her PhD\, she mainly w orked on developing data-efficient natural language processing~(NLP) syste ms. She has made several contributions in data selection\, data representa tion\, and model adaptation for multilingual NLP.
DTSTART;TZID=America/New_York:20240308T120000 DTEND;TZID=America/New_York:20240308T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Cindy Wang (Google DeepMind) “Building Data-Efficient and Reliable Applications with Large Language Models” URL:https://www.clsp.jhu.edu/events/cindy-wang-google-deepmind-building-dat a-efficient-and-reliable-applications-with-large-language-models/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2024\,March\,Wang END:VEVENT BEGIN:VEVENT UID:ai1ec-24479@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Student Seminars CONTACT: DESCRIPTION:Abstract
\nT he speech field is evolving to solve more challenging scenarios\, such as multi-channel recordings with multiple simultaneous talkers. Given the man y types of microphone setups out there\, we present the UniX-Encoder. It’s a universal encoder designed for multiple tasks\, and worked with any mic rophone array\, in both solo and multi-talker environments. Our research e nhances previous multichannel speech processing efforts in four key areas: 1) Adaptability: Contrasting traditional models constrained to certain mi crophone array configurations\, our encoder is universally compatible. 2) MultiTask Capability: Beyond the single-task focus of previous systems\, U niX-Encoder acts as a robust upstream model\, adeptly extracting features for diverse tasks including ASR and speaker recognition. 3) Self-Supervise d Training: The encoder is trained without requiring labeled multi-channel data. 4) End-to-End Integration: In contrast to models that first beamfor m then process single-channels\, our encoder offers an end-to-end solution \, bypassing explicit beamforming or separation. To validate its effective ness\, we tested the UniXEncoder on a synthetic multi-channel dataset from the LibriSpeech corpus. Across tasks like speech recognition and speaker diarization\, our encoder consistently outperformed combinations like the WavLM model with the BeamformIt frontend.
DTSTART;TZID=America/New_York:20240311T200500 DTEND;TZID=America/New_York:20240311T210500 SEQUENCE:0 SUMMARY:Zili Huang (JHU) “Unix-Encoder: A Universal X-Channel Speech Encode r for Ad-Hoc Microphone Array Speech Processing” URL:https://www.clsp.jhu.edu/events/zili-huang-jhu-unix-encoder-a-universal -x-channel-speech-encoder-for-ad-hoc-microphone-array-speech-processing/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2024\,Huang\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-24481@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:Abstract
\nNatural language provides an intuitive and powerful interface to access knowledge at scale. Modern l anguage systems draw information from two rich knowledge sources: (1) info rmation stored in their parameters during massive pretraining and (2) docu ments retrieved at inference time. Yet\, we are far from building systems that can reliably provide information from such knowledge sources. In this talk\, I will discuss paths for more robust systems. In the first part of the talk\, I will present a module for scaling retrieval-based knowledge augmentation. We learn a compressor that maps retrieved documents into tex tual summaries prior to in-context integration. This not only reduces the computational costs but also filters irrelevant or incorrect information. In the second half of the talk\, I will discuss the challenges of updating knowledge stored in model parameters and propose a method to prevent mode ls from reciting outdated information by identifying facts that are prone to rapid change. I will conclude my talk by proposing an interactive syste m that can elicit information from users when needed.
\nBiog raphy
\nEunsol Choi is an assistant pro fessor in the Computer Science department at the University of Texas at Au stin. Prior to UT\, she spent a year at Google AI as a visiting researcher . Her research area spans natural language processing and machine learning . She is particularly interested in interpreting and reasoning about text in a dynamic real world context. She is a recipient of a Facebook research fellowship\, Google faculty research award\, Sony faculty award\, and an outstanding paper award at EMNLP. She received a Ph.D. in computer science and engineering from University of Washington and B.A in mathematics and computer science from Cornell University.
\nDTSTART;TZID=America/New_York:20240315T120000 DTEND;TZID=America/New_York:20240315T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21209 SEQUENCE:0 SUMMARY:Eunsol Choi (University of Texas at Austin) “Knowledge-Rich Languag e Systems in a Dynamic World” URL:https://www.clsp.jhu.edu/events/eunsol-choi-university-of-texas-at-aust in-knowledge-rich-language-systems-in-a-dynamic-world/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2024\,Choi\,March END:VEVENT BEGIN:VEVENT UID:ai1ec-24489@www.clsp.jhu.edu DTSTAMP:20240329T133023Z CATEGORIES;LANGUAGE=en-US:Seminars CONTACT: DESCRIPTION:
Abstract
\nOver the past decade\, the field of Speech Generation has seen significant progress in enhancing spe ech quality and naturalness. Despite these advancements\, persistent chall enges such as speech noise\, limited high-quality data availability\, and the lack of robustness in speech generation systems remain. Additionally\, the evaluation of speech presents a significant obstacle for comprehensiv e assessment at scale. Concurrently\, recent breakthroughs in Large Langua ge Models (LLMs) have revolutionized text generation and natural language processing. However\, the complexity of spoken language introduces unique hurdles\, including managing long speech waveform sequences. In this prese ntation\, I will explore recent innovations in speech synthesis with spoke n language modeling\, evaluation for generative speech systems and high-fi delity speech enhancement. Finally\, I will discuss prospective avenues fo r future research aimed at addressing these challenges.
\nBi o
\nSoumi Maiti is a postdoctoral researcher at Language Te chnologies Institute\, Carnegie Mellon University\, where she works on spe ech and language processing. Her research broadly focuses on building inte lligent systems that can communicate with humans naturally. She earned a Ph.D. from the Graduate Center\, City University of New York (CUNY) with t he Graduate Center Fellowship advised by Prof Michael Mandel. She earned h er B.Tech. in Computer Science from the Indian Institute of Engineering Sc ience and Technology\, Shibpur. Previously\, she has worked in the Text-To -Speech team at Apple. She has also worked at Google and Interactions LLC as a student researcher and research intern. She has worked as an adjunct lecturer at Brooklyn College\, CUNY\, for three years and served as a Math Fellow at Hunter College. She has served as session chair in ICASSP 2024\ , ICASSP 2023\, SLT 2023 and others\, and area chair at EMNLP 2023.
\n< p> DTSTART;TZID=America/New_York:20240329T120000 DTEND;TZID=America/New_York:20240329T131500 LOCATION:Hackerman Hall B17 @ 3400 N. Charles Street\, Baltimore\, MD 21218 SEQUENCE:0 SUMMARY:Soumi Maiti (CMU) “Towards Robust Speech Generation” URL:https://www.clsp.jhu.edu/events/soumi-maiti/ X-COST-TYPE:free X-TAGS;LANGUAGE=en-US:2024\,Maiti\,March END:VEVENT END:VCALENDAR