arXiv subjects

Ryan Price

Publications and source records attributed to Ryan Price.

5 recordsLinked to original sources

arXiv2023

Trustera: A Live Conversation Redaction System

Trustera, the first functional system that redacts personally identifiable information (PII) in real-time spoken conversations to remove agents' need to hear sensitive information while preserving the naturalness of live customer-agent conversations. As opposed to post-call redaction, audio masking starts as soon as the customer begins speaking to a PII entity. This significantly reduces the risk of PII being intercepted or stored in insecure data storage. Trustera's architecture consists of a pipeline of automatic speech recognition, natural language understanding, and a live audio redactor module. The system's goal is three-fold: redact entities that are PII, mask the audio that goes to the agent, and at the same time capture the entity, so that the captured PII can be used for a payment transaction or caller identification. Trustera is currently being used by thousands of agents to secure customers' sensitive information.

cs.CL↗

arXiv2022

Cross-stitched Multi-modal Encoders

In this paper, we propose a novel architecture for multi-modal speech and text input. We combine pretrained speech and text encoders using multi-headed cross-modal attention and jointly fine-tune on the target problem. The resultant architecture can be used for continuous token-level classification or utterance-level prediction acting on simultaneous text and speech. The resultant encoder efficiently captures both acoustic-prosodic and lexical information. We compare the benefits of multi-headed attention-based fusion for multi-modal utterance-level classification against a simple concatenation of pre-pooled, modality-specific representations. Our model architecture is compact, resource efficient, and can be trained on a single consumer GPU card.

cs.CL↗

arXiv2022

Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture

Person name capture from human speech is a difficult task in human-machine conversations. In this paper, we propose a novel approach to capture the person names from the caller utterances in response to the prompt "say and spell your first/last name". Inspired from work on spell correction, disfluency removal and text normalization, we propose a lightweight Seq-2-Seq system which generates a name spell from a varying user input. Our proposed method outperforms the strong baseline which is based on LM-driven rule-based approach.

cs.CL↗

arXiv2011

Haar wavelets as a tool for the statistical characterization of variability

In the field of gamma-ray astronomy, irregular and noisy datasets make difficult the characterization of light-curve features in terms of statistical significance while properly accounting for trial factors associated with the search for variability at different times and over different timescales. In order to address these difficulties, we propose a method based on the Haar wavelet decomposition of the data. It allows statistical characterization of possible variability, embedded in a white noise background, in terms of a confidence level. The method is applied to artificially generated data for characterization as well as to the the very high energy M87 light curve recorded with VERITAS in 2008 which serves here as a realistic application example.

astro-ph.IM↗

arXiv2010

Stellar intensity interferometry: Experimental steps toward long-baseline observations

Experiments are in progress to prepare for intensity interferometry with arrays of air Cherenkov telescopes. At the Bonneville Seabase site, near Salt Lake City, a testbed observatory has been set up with two 3-m air Cherenkov telescopes on a 23-m baseline. Cameras are being constructed, with control electronics for either off- or online analysis of the data. At the Lund Observatory (Sweden), in Technion (Israel) and at the University of Utah (USA), laboratory intensity interferometers simulating stellar observations have been set up and experiments are in progress, using various analog and digital correlators, reaching 1.4 ns time resolution, to analyze signals from pairs of laboratory telescopes.

astro-ph.IM↗