1 citations · 5 across the 20 of their papers we have counts for
20 papers
Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance
Or Biton, Tomer Krichli, Itai Allouche +1
Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably leading to alignment failures. T…
Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming
Rotem Rousso, Eyal Cohen, Joseph Keshet
Recent advances in sequence modeling have significantly improved ASR systems, bringing them close to human-level recognition accuracy and enhancing robustness across diverse acoust…
Why Sampling Is Not Choosing: Intentionality, Agency, and Moral Responsibility in Large Language Models
Joseph Keshet
Recent advances in large language models (LLMs) have prompted claims that such systems exhibit agency or qualify as moral agents. This paper argues that these attributions are misg…
Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming
Roy Weber, Meidan Zehavi, Rotem Rousso +1
We present a method for accurate multilingual word-level forced alignment, consisting of an alignment encoder and a learned alignment decoder. The encoder integrates two representa…
Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time
Itai Allouche, Joseph Keshet
Multimodal large language models (MLLMs) achieve strong performance on vision- and audio-language tasks, yet can generate responses that conflict with the given visual or auditory…
Joint Enhancement and Classification using Coupled Diffusion Models of Signals and Logits
Gilad Nurko, Roi Benita, Yehoshua Dissen +4
Robust classification in noisy environments remains a fundamental challenge in machine learning. Standard approaches typically treat signal enhancement and classification as separa…
Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models
Roi Benita, Michael Elad, Joseph Keshet
Recovering a signal from its degraded measurements is a long standing challenge in science and engineering. Recently, zero-shot diffusion based methods have been proposed for such…
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…
WhisperRT -- Turning Whisper into a Causal Streaming Model
Tomer Krichli, Bhiksha Raj, Joseph Keshet
Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcri…
UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching
Neta Glazer, Aviv Navon, Yael Segal +6
Recent advances in Text-to-Speech (TTS) have enabled highly natural speech synthesis, yet integrating speech with complex background environments remains challenging. We introduce…
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…
Spectral Analysis of Diffusion Models with Application to Schedule Design
Roi Benita, Michael Elad, Joseph Keshet
Diffusion models (DMs) have emerged as powerful tools for modeling complex data distributions and generating realistic new samples. Over the years, advanced architectures and sampl…
Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR
Yael Segal-Feldman, Aviv Shamsian, Aviv Navon +2
Large transformer-based models have significant potential for speech transcription and translation. Their self-attention mechanisms and parallel processing enable them to capture c…
WhisperNER: Unified Open Named Entity and Speech Recognition
Gil Ayache, Menachem Pirchi, Aviv Navon +3
Integrating named entity recognition (NER) with automatic speech recognition (ASR) can significantly enhance transcription accuracy and informativeness. In this paper, we introduce…
Tradition or Innovation: A Comparison of Modern ASR Methods for Forced Alignment
Rotem Rousso, Eyal Cohen, Joseph Keshet +1
Forced alignment (FA) plays a key role in speech research through the automatic time alignment of speech signals with corresponding text transcriptions. Despite the move towards en…
Enhanced ASR Robustness to Packet Loss with a Front-End Adaptation Network
Yehoshua Dissen, Shiry Yonash, Israel Cohen +1
In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but th…
Keyword-Guided Adaptation of Automatic Speech Recognition
Aviv Shamsian, Aviv Navon, Neta Glazer +2
Automatic Speech Recognition (ASR) technology has made significant progress in recent years, providing accurate transcription across various domains. However, some challenges remai…
Combining Language Models For Specialized Domains: A Colorful Approach
Daniel Eitan, Menachem Pirchi, Neta Glazer +7
General purpose language models (LMs) encounter difficulties when processing domain-specific jargon and terminology, which are frequently utilized in specialized fields such as med…
DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
Roi Benita, Michael Elad, Joseph Keshet
Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further requir…