Related papers: MDM-ASR: Bridging Accuracy and Efficiency in ASR w…

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling. However, MDMs are known to learn substantially more slowly than ARMs, which may become problematic when scaling…

We introduce a deep learning (DL) framework for inverse problems in imaging, and demonstrate the advantages and applicability of this approach in passive synthetic aperture radar (SAR) image reconstruction. We interpret image recon-…

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

Machine translation systems are conventionally trained on textual resources that do not model phenomena that occur in spoken language. While the evaluation of neural machine translation systems on textual inputs is actively researched in…

Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Speculative decoding mitigates this cost through a draft-verify…

Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint…

Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the…

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…

End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…

Large language model (LLM)-based automatic speech recognition (ASR) has recently attracted a lot of attention due to its high recognition accuracy and enhanced multi-dialect support. However, the high decoding latency of LLMs challenges the…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Self-supervised learning has garnered increasing attention in time series analysis for benefiting various downstream tasks and reducing reliance on labeled data. Despite its effectiveness, existing methods often struggle to comprehensively…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

Multivariate network time series are ubiquitous in modern systems, yet existing network autoregressive models typically treat nodes as scalar processes, ignoring cross-variable spillovers. To capture these complex interactions without the…

The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Diffusion-based super-resolution (SR) models have recently garnered significant attention due to their potent restoration capabilities. But conventional diffusion models perform noise sampling from a single distribution, constraining their…

Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an…

Speech applications in far-field real world settings often deal with signals that are corrupted by reverberation. The task of dereverberation constitutes an important step to improve the audible quality and to reduce the error rates in…

Much recent effort has been invested in non-autoregressive neural machine translation, which appears to be an efficient alternative to state-of-the-art autoregressive machine translation on modern GPUs. In contrast to the latter, where…