Related papers: Composing Copyless Streaming String Transducers

Linear extended top-down tree transducers (or synchronous tree-substitution grammars) are popular formal models of tree transformations. The expressive power of compositions of such transducers with and without regular look-ahead is…

Using end-to-end models for speech translation (ST) has increasingly been the focus of the ST community. These models condense the previously cascaded systems by directly converting sound waves into translated text. However, cascaded models…

While the neural transducer is popular for online speech recognition, simultaneous speech translation (SST) requires both streaming and re-ordering capabilities. This paper presents the LS-Transducer-SST, a label-synchronous neural…

To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens…

Diffusion models have emerged as the dominant paradigm for style transfer, but their text-driven mechanism is hindered by a core limitation: it treats textual descriptions as uniform, monolithic guidance. This limitation overlooks the…

The rigid, uniform allocation of computation in standard Transformer (TF) architectures can limit their efficiency and scalability, particularly for large-scale models and long sequences. Addressing this, we introduce Subjective Depth…

Text Style Transfer (TST) is performable through approaches such as latent space disentanglement, cycle-consistency losses, prototype editing etc. The prototype editing approach, which is known to be quite successful in TST, involves two…

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

The iterative sampling procedure employed by diffusion models (DMs) often leads to significant inference latency. To address this, we propose Stochastic Consistency Distillation (SCott) to enable accelerated text-to-image generation, where…

Representing symbolic music with compound tokens, where each token consists of several different sub-tokens representing a distinct musical feature or attribute, offers the advantage of reducing sequence length. While previous research has…

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

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.…

Text style transfer is the task of transferring the style of text having certain stylistic attributes, while preserving non-stylistic or content information. In this work we introduce the Generative Style Transformer (GST) - a new approach…

We propose an innovative, learnable two-sided short-time Laplace transform (STLT) mechanism to supplant the traditional self attention in transformer-based LLMs. Our STLT introduces trainable parameters for each Laplace node, enabling…

Streaming generation models are utilized across fields, with the Transducer architecture being popular in industrial applications. However, its input-synchronous decoding mechanism presents challenges in tasks requiring non-monotonic…

Streaming speech translation (StreamST) requires determining appropriate timing, known as policy, to generate translations while continuously receiving source speech inputs, balancing low latency with high translation quality. However,…

Edit-based approaches have recently shown promising results on multiple monolingual sequence transduction tasks. In contrast to conventional sequence-to-sequence (Seq2Seq) models, which learn to generate text from scratch as they are…

Modern language models define distributions over strings, but downstream tasks often require different output formats. For instance, a model that generates byte-pair strings does not directly produce word-level predictions, and a DNA model…

String-to-string MSO interpretations are like Courcelle's MSO transductions, except that a single output position can be represented using a tuple of input positions instead of just a single input position. In particular, the output length…

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…