English
Related papers

Related papers: Streaming Transformations of Infinite Ordered-Data…

200 papers

Streaming multi-talker speech translation is a task that involves not only generating accurate and fluent translations with low latency but also recognizing when a speaker change occurs and what the speaker's gender is. Speaker change…

Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR…

Computation and Language · Computer Science 2023-10-23 Peidong Wang , Eric Sun , Jian Xue , Yu Wu , Long Zhou , Yashesh Gaur , Shujie Liu , Jinyu Li

We study the sequence-to-sequence mapping capacity of transformers by relating them to finite transducers, and find that they can express surprisingly large classes of transductions. We do so using variants of RASP, a programming language…

Formal Languages and Automata Theory · Computer Science 2024-11-07 Lena Strobl , Dana Angluin , David Chiang , Jonathan Rawski , Ashish Sabharwal

We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…

Computation and Language · Computer Science 2018-01-04 Kanishka Rao , Haşim Sak , Rohit Prabhavalkar

The Streaming Unmixing and Recognition Transducer (SURT) has recently become a popular framework for continuous, streaming, multi-talker speech recognition (ASR). With advances in architecture, objectives, and mixture simulation methods, it…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-30 Desh Raj , Matthew Wiesner , Matthew Maciejewski , Leibny Paola Garcia-Perera , Daniel Povey , Sanjeev Khudanpur

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

We study the fundamental issue of decidability of satisfiability over string logics with concatenations and finite-state transducers as atomic operations. Although restricting to one type of operations yields decidability, little is known…

Logic in Computer Science · Computer Science 2015-11-06 Anthony W. Lin , Pablo Barcelo

We introduce a logic, called LT, to express properties of transductions, i.e. binary relations from input to output (finite) words. In LT, the input/output dependencies are modelled via an origin function which associates to any position of…

Formal Languages and Automata Theory · Computer Science 2018-05-31 Luc Dartois , Emmanuel Filiot , Nathan Lhote

Regular functions from infinite words to infinite words can be equivalently specified by MSO-transducers, streaming $\omega$-string transducers as well as deterministic two-way transducers with look-ahead. In their one-way restriction, the…

Formal Languages and Automata Theory · Computer Science 2024-09-19 V. Dave , E. Filiot , S. Krishna , N. Lhote

The Scene Representation Transformer (SRT) is a recent method to render novel views at interactive rates. Since SRT uses camera poses with respect to an arbitrarily chosen reference camera, it is not invariant to the order of the input…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Aleksandr Safin , Daniel Duckworth , Mehdi S. M. Sajjadi

Transformers have emerged as a prominent model framework for audio tagging (AT), boasting state-of-the-art (SOTA) performance on the widely-used Audioset dataset. However, their impressive performance often comes at the cost of high memory…

Sound · Computer Science 2024-06-11 Heinrich Dinkel , Zhiyong Yan , Yongqing Wang , Junbo Zhang , Yujun Wang , Bin Wang

Regular expressions are a classical concept in formal language theory. Regular expressions in programming languages (RegEx) such as JavaScript, feature non-standard semantics of operators (e.g. greedy/lazy Kleene star), as well as…

BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its…

Computation and Language · Computer Science 2019-10-25 Raghavendra Pappagari , Piotr Żelasko , Jesús Villalba , Yishay Carmiel , Najim Dehak

Rapid technological advances are inherently linked to the increased amount of data, a substantial portion of which can be interpreted as data stream, capable of exhibiting the phenomenon of concept drift and having a high imbalance ratio.…

Machine Learning · Computer Science 2024-04-25 Paweł Zyblewski

Simultaneous Machine Translation is the task of incrementally translating an input sentence before it is fully available. Currently, simultaneous translation is carried out by translating each sentence independently of the previously…

Computation and Language · Computer Science 2022-04-01 Javier Iranzo-Sánchez , Jorge Civera , Alfons Juan

In large-scale applications including medical imaging, collocation differential equation solvers, and estimation with differential privacy, the underlying linear inverse problem can be reformulated as a streaming problem. In theory, the…

Numerical Analysis · Mathematics 2024-01-31 Nathaniel Pritchard , Vivak Patel

The class of regular transformations has several equivalent characterizations such as functional MSO transductions, deterministic two-way transducers, streaming string transducers, as well as regular transducer expressions (RTE). For…

Formal Languages and Automata Theory · Computer Science 2022-02-10 Luc Dartois , Paul Gastin , R. Govind , Shankaranarayanan Krishna

Functional transductions realized by two-way transducers (equivalently, by streaming transducers and by MSO transductions) are the natural and standard notion of "regular" mappings from words to words. It was shown recently (LICS'13) that…

Formal Languages and Automata Theory · Computer Science 2017-01-11 Félix Baschenis , Olivier Gauwin , Anca Muscholl , Gabriele Puppis

We present a system for Complex Event Recognition (CER) based on automata. While multiple such systems have been described in the literature, they typically suffer from a lack of clear and denotational semantics, a limitation which often…

Formal Languages and Automata Theory · Computer Science 2024-07-04 Elias Alevizos , Alexander Artikis , Georgios Paliouras

This paper proposes a token-level serialized output training (t-SOT), a novel framework for streaming multi-talker automatic speech recognition (ASR). Unlike existing streaming multi-talker ASR models using multiple output branches, the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-18 Naoyuki Kanda , Jian Wu , Yu Wu , Xiong Xiao , Zhong Meng , Xiaofei Wang , Yashesh Gaur , Zhuo Chen , Jinyu Li , Takuya Yoshioka