Related papers: On Streaming String Transducers and HDT0L Systems

End-to-end spoken language understanding (SLU) remains elusive even with current large pretrained language models on text and speech, especially in multilingual cases. Machine translation has been established as a powerful pretraining…

Understanding how visual information is encoded in biological and artificial systems often requires vision scientists to generate appropriate stimuli to test specific hypotheses. Although deep neural network models have revolutionized the…

This paper presents Scalable Semantic Transfer (SST), a novel training paradigm, to explore how to leverage the mutual benefits of the data from different label domains (i.e. various levels of label granularity) to train a powerful human…

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Structured State Spaces for Sequences (S4) is a recently proposed sequence model with successful applications in various tasks, e.g. vision, language modeling, and audio. Thanks to its mathematical formulation, it compresses its input to a…

End-to-end speech translation (ST) for conversation recordings involves several under-explored challenges such as speaker diarization (SD) without accurate word time stamps and handling of overlapping speech in a streaming fashion. In this…

Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. As a result, SSL holds the promise to learn representations from data in-the-wild, i.e., without the…

Finite-State Transducers (FSTs) are effective models for string-to-string rewriting tasks, often providing the efficiency necessary for high-performance applications, but constructing transducers by hand is difficult. In this work, we…

Transformers have become the dominant architecture for sequence modeling tasks such as natural language processing or audio processing, and they are now even considered for tasks that are not naturally sequential such as image…

Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize…

Attention-based models have been gaining popularity recently for their strong performance demonstrated in fields such as machine translation and automatic speech recognition. One major challenge of attention-based models is the need of…

In streaming scenarios, models must learn continuously, adapting to concept drifts without erasing previously acquired knowledge. However, existing research communities address these challenges in isolation. Continual Learning (CL) focuses…

Some of the most relevant document schemas used online, such as XML and JSON, have a nested format. In the last decade, the task of extracting data from nested documents over streams has become especially relevant. We focus on the streaming…

Self-attention mechanisms have enabled transformers to achieve superhuman-level performance on many speech-to-text (STT) tasks, yet the challenge of automatic prosodic segmentation has remained unsolved. In this paper we finetune Whisper, a…

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…

Tree transductions are binary relations of finite trees. For tree transductions defined by non-deterministic top-down tree transducers, inclusion, equivalence and synthesis problems are known to be undecidable. Adding origin semantics to…

Voice style conversion aims to transform an input utterance to match a target speaker's timbre, accent, and emotion, with a central challenge being the disentanglement of linguistic content from style. While prior work has explored this…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

In Spoken Language Understanding (SLU) the task is to extract important information from audio commands, like the intent of what a user wants the system to do and special entities like locations or numbers. This paper presents a simple…

Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to…