相关论文: A Multiplexed Network for End-to-End, Multilingual…

Code-switching-where multilingual speakers alternately switch between languages during conversations-still poses significant challenges to end-to-end (E2E) automatic speech recognition (ASR) systems due to phenomena of both acoustic and…

Modularity plays a crucial role in the development and maintenance of complex systems. While end-to-end text spotting efficiently mitigates the issues of error accumulation and sub-optimal performance seen in traditional two-step…

Fast inference speed is an important goal towards real-world deployment of speech translation (ST) systems. End-to-end (E2E) models based on the encoder-decoder architecture are more suitable for this goal than traditional cascaded systems,…

Streaming processing of speech audio is required for many contemporary practical speech recognition tasks. Even with the large corpora of manually transcribed speech data available today, it is impossible for such corpora to cover…

This paper proposes a model for transforming speech features using the frequency-directional attention model for End-to-End (E2E) automatic speech recognition. The idea is based on the hypothesis that in the phoneme system of each language,…

Recent research in the field of text localization in a resource constrained environment has made extensive use of deep neural networks. Scene text localization and recognition on low-memory mobile devices have a wide range of applications…

It is known that a deep neural network model pre-trained with large-scale data greatly improves the accuracy of various tasks, especially when there are resource constraints. However, the information needed to solve a given task can vary,…

We present Mu$^{2}$SLAM, a multilingual sequence-to-sequence model pre-trained jointly on unlabeled speech, unlabeled text and supervised data spanning Automatic Speech Recognition (ASR), Automatic Speech Translation (AST) and Machine…

In this paper, we propose Multi$^2$OIE, which performs open information extraction (open IE) by combining BERT with multi-head attention. Our model is a sequence-labeling system with an efficient and effective argument extraction method. We…

Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and document summarization. This paper addresses the challenges of achieving high long-context…

Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user's playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during…

End-to-end multi-talker speech recognition has garnered great interest as an effective approach to directly transcribe overlapped speech from multiple speakers. Current methods typically adopt either 1) single-input multiple-output (SIMO)…

In recent years, the field of Handwritten Text Recognition (HTR) has seen the emergence of various new models, each claiming to perform competitively better than the other in specific scenarios. However, making a fair comparison of these…

Soft prompts have emerged as a powerful alternative to adapters in parameter-efficient fine-tuning (PEFT), enabling large language models (LLMs) to adapt to downstream tasks without architectural changes or parameter updates. While prior…

This paper describes progress towards making a Neural Text-to-Speech (TTS) Frontend that works for many languages and can be easily extended to new languages. We take a Machine Translation (MT) inspired approach to constructing the…

Named entity recognition (NER) from text has been a widely studied problem and usually extracts semantic information from text. Until now, NER from speech is mostly studied in a two-step pipeline process that includes first applying an…

The requirements for many applications of state-of-the-art speech recognition systems include not only low word error rate (WER) but also low latency. Specifically, for many use-cases, the system must be able to decode utterances in a…

In autonomous driving, end-to-end (E2E) driving systems that predict control commands directly from sensor data have achieved significant advancements. For safe driving in unexpected scenarios, these systems may additionally rely on human…

Text spotting in natural scene images is of great importance for many image understanding tasks. It includes two sub-tasks: text detection and recognition. In this work, we propose a unified network that simultaneously localizes and…

In this paper, we propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em attention bridge} that is shared across all languages. That is,…