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-21494@www.clsp.jhu.edu DTSTAMP:20240330T034744Z CATEGORIES;LANGUAGE=en-US:Student Seminars CONTACT: DESCRIPTION:
Abstract
\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:20240330T034744Z 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-21616@www.clsp.jhu.edu DTSTAMP:20240330T034744Z 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-23555@www.clsp.jhu.edu DTSTAMP:20240330T034744Z 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-24461@www.clsp.jhu.edu DTSTAMP:20240330T034744Z CATEGORIES;LANGUAGE=en-US:Student Seminars CONTACT: DESCRIPTION:Abstract
\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-24479@www.clsp.jhu.edu DTSTAMP:20240330T034744Z 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 END:VCALENDAR