5 papers
Discrete Tokenization Unlocks Transformers for Calibrated Tabular Forecasting
Yael S. Elmatad
Gradient boosting still dominates Transformers on tabular benchmarks. Our tokenizer uses a deliberately simplistic discretized vocabulary so we can highlight how even basic tokeniz…
Drax: Speech Recognition with Discrete Flow Matching
Aviv Navon, Aviv Shamsian, Neta Glazer +4
Diffusion and flow-based non-autoregressive (NAR) models have shown strong promise in large language modeling, however, their potential for automatic speech recognition (ASR) remai…
Beyond Transcription: Mechanistic Interpretability in ASR
Neta Glazer, Yael Segal-Feldman, Hilit Segev +6
Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error…
Keyword Spotting with Hyper-Matched Filters for Small Footprint Devices
Yael Segal-Feldman, Ann R. Bradlow, Matthew Goldrick +1
Open-vocabulary keyword spotting (KWS) refers to the task of detecting words or terms within speech recordings, regardless of whether they were included in the training data. This…
FlowTSE: Target Speaker Extraction with Flow Matching
Aviv Navon, Aviv Shamsian, Yael Segal-Feldman +3
Target speaker extraction (TSE) aims to isolate a specific speaker's speech from a mixture using speaker enrollment as a reference. While most existing approaches are discriminativ…