English
Related papers

Related papers: NUTS, NARS, and Speech

200 papers

End-to-end (E2E) systems for automatic speech recognition (ASR), such as RNN Transducer (RNN-T) and Listen-Attend-Spell (LAS) blend the individual components of a traditional hybrid ASR system - acoustic model, language model, pronunciation…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Mahaveer Jain , Gil Keren , Jay Mahadeokar , Geoffrey Zweig , Florian Metze , Yatharth Saraf

Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-31 Alejandro Gomez-Alanis , Lukas Drude , Andreas Schwarz , Rupak Vignesh Swaminathan , Simon Wiesler

Neural machine translation models have shown to achieve high quality when trained and fed with well structured and punctuated input texts. Unfortunately, the latter condition is not met in spoken language translation, where the input is…

Computation and Language · Computer Science 2019-10-24 Mattia Antonino Di Gangi , Robert Enyedi , Alessandra Brusadin , Marcello Federico

Convolutional neural networks are sensitive to unknown noisy condition in the test phase and so their performance degrades for the noisy data classification task including noisy speech recognition. In this research, a new convolutional…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-01 Elyas Rashno , Ahmad Akbari , Babak Nasersharif

Non-autoregressive Transformers (NATs) are recently applied in direct speech-to-speech translation systems, which convert speech across different languages without intermediate text data. Although NATs generate high-quality outputs and…

Computation and Language · Computer Science 2024-10-23 Weiting Tan , Jingyu Zhang , Lingfeng Shen , Daniel Khashabi , Philipp Koehn

This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differentiable NAS approach to optimize the structure of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-21 David Peter , Wolfgang Roth , Franz Pernkopf

We introduce a novel neural network module that adeptly handles recursive data flow in neural network architectures. At its core, this module employs a self-consistent approach where a set of recursive equations is solved iteratively,…

Computation and Language · Computer Science 2024-10-07 Konstantin Kolokolov , Pavel Pekichev , Karthik Raghunathan

Spiking Neural Networks (SNNs) are distributed trainable systems whose computing elements, or neurons, are characterized by internal analog dynamics and by digital and sparse synaptic communications. The sparsity of the synaptic spiking…

Signal Processing · Electrical Eng. & Systems 2019-10-22 Hyeryung Jang , Osvaldo Simeone , Brian Gardner , André Grüning

Voice controlled virtual assistants (VAs) are now available in smartphones, cars, and standalone devices in homes. In most cases, the user needs to first "wake-up" the VA by saying a particular word/phrase every time he or she wants the VA…

Human-Computer Interaction · Computer Science 2019-02-05 Atta Norouzian , Bogdan Mazoure , Dermot Connolly , Daniel Willett

Modern non-autoregressive~(NAR) speech recognition systems aim to accelerate the inference speed; however, they suffer from performance degradation compared with autoregressive~(AR) models as well as the huge model size issue. We propose a…

Sound · Computer Science 2022-07-22 Xun Gong , Zhikai Zhou , Yanmin Qian

Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationally expensive sampling strategies, limiting their practical…

Computation and Language · Computer Science 2026-01-28 Fangan Dong , Zuming Yan , Xuri Ge , Zhiwei Xu , Mengqi Zhang , Xuanang Chen , Ben He , Xin Xin , Zhumin Chen , Ying Zhou

Current sparse neural information retrieval (IR) methods, and to a lesser extent more traditional models such as BM25, do not take into account the document collection and the complex interplay between different term weights when…

Information Retrieval · Computer Science 2025-05-08 Arthur Satouf , Gabriel Ben Zenou , Benjamin Piwowarski , Habiboulaye Amadou Boubacar , Pablo Piantanida

Large self-supervised pre-trained speech models require computationally expensive fine-tuning for downstream tasks. Soft prompt tuning offers a simple parameter-efficient alternative by utilizing minimal soft prompt guidance, enhancing…

Sequence to Sequence models, in particular the Transformer, achieve state of the art results in Automatic Speech Recognition. Practical usage is however limited to cases where full utterance latency is acceptable. In this work we introduce…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-25 George Sterpu , Christian Saam , Naomi Harte

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb

Neural Architecture Search (NAS) has recently become a topic of great interest. However, there is a potentially impactful issue within NAS that remains largely unrecognized: noise. Due to stochastic factors in neural network initialization,…

Neural and Evolutionary Computing · Computer Science 2022-05-03 Arkadiy Dushatskiy , Tanja Alderliesten , Peter A. N. Bosman

A deep neural network (DNN)-based model has been developed to predict non-parametric distributions of durations of phonemes in specified phonetic contexts and used to explore which factors influence durations most. Major factors in US…

Sound · Computer Science 2019-09-09 Xizi Wei , Melvyn Hunt , Adrian Skilling

In multi-turn dialogs, natural language understanding models can introduce obvious errors by being blind to contextual information. To incorporate dialog history, we present a neural architecture with Speaker-Sensitive Dual Memory Networks…

Computation and Language · Computer Science 2017-11-30 Young-Bum Kim , Sungjin Lee , Ruhi Sarikaya

Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…

Computation and Language · Computer Science 2016-09-16 Peng Dai , Xue Teng , Frank Rudzicz , Ing Yann Soon

Wearable devices like smart glasses are approaching the compute capability to seamlessly generate real-time closed captions for live conversations. We build on our recently introduced directional Automatic Speech Recognition (ASR) for smart…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-22 Ju Lin , Niko Moritz , Yiteng Huang , Ruiming Xie , Ming Sun , Christian Fuegen , Frank Seide
‹ Prev 1 4 5 6 7 8 10 Next ›