中文
相关论文

相关论文: Multilingual Adaptation of RNN Based ASR Systems

200 篇论文

Non-autoregressive (NAR) models for automatic speech recognition (ASR) aim to achieve high accuracy and fast inference by simplifying the autoregressive (AR) generation process of conventional models. Connectionist temporal classification…

音频与语音处理 · 电气工程与系统科学 2024-03-29 Yuya Fujita , Shinji Watanabe , Xuankai Chang , Takashi Maekaku

Inspired by the progress of the End-to-End approach [1], this paper systematically studies the effects of Number of Filters of convolutional layers on the model prediction accuracy of CNN+RNN (Convolutional Neural Networks adding to…

机器学习 · 计算机科学 2021-02-05 James Mou , Jun Li

Foreign accent conversion (FAC) in speech processing remains a challenging task. Building on the remarkable success of large language models (LLMs) in Text-to-Speech (TTS) tasks, this study investigates the adaptation of LLM-based…

音频与语音处理 · 电气工程与系统科学 2025-07-09 Zhuangfei Cheng , Guangyan Zhang , Zehai Tu , Yangyang Song , Shuiyang Mao , Xiaoqi Jiao , Jingyu Li , Yiwen Guo , Jiasong Wu

This paper proposed a class of novel Deep Recurrent Neural Networks which can incorporate language-level information into acoustic models. For simplicity, we named these networks Recurrent Deep Language Networks (RDLNs). Multiple variants…

计算与语言 · 计算机科学 2020-11-12 Peidong Wang , Deliang Wang

Multimodal language models attempt to incorporate non-linguistic features for the language modeling task. In this work, we extend a standard recurrent neural network (RNN) language model with features derived from videos. We train our…

计算与语言 · 计算机科学 2019-03-08 Antonios Anastasopoulos , Shankar Kumar , Hank Liao

Building multilingual and crosslingual models help bring different languages together in a language universal space. It allows models to share parameters and transfer knowledge across languages, enabling faster and better adaptation to a…

计算与语言 · 计算机科学 2019-02-21 Siddharth Dalmia , Xinjian Li , Alan W Black , Florian Metze

Automatic Phoneme Recognition (APR) systems are often trained using pseudo phoneme-level annotations generated from text through Grapheme-to-Phoneme (G2P) systems. These G2P systems frequently output multiple possible pronunciations per…

音频与语音处理 · 电气工程与系统科学 2025-09-09 Henry Grafé , Hugo Van hamme

The goal of language modeling techniques is to capture the statistical and structural properties of natural languages from training corpora. This task typically involves the learning of short range dependencies, which generally model the…

计算与语言 · 计算机科学 2017-08-23 Youssef Oualil , Mittul Singh , Clayton Greenberg , Dietrich Klakow

Language models (LMs) have been commonly adopted to boost the performance of automatic speech recognition (ASR) particularly in domain adaptation tasks. Conventional way of LM training treats all the words in corpora equally, resulting in…

计算与语言 · 计算机科学 2023-10-18 Yingyi Ma , Zhe Liu , Ozlem Kalinli

Change detection is one of the central problems in earth observation and was extensively investigated over recent decades. In this paper, we propose a novel recurrent convolutional neural network (ReCNN) architecture, which is trained to…

计算机视觉与模式识别 · 计算机科学 2019-03-27 Lichao Mou , Lorenzo Bruzzone , Xiao Xiang Zhu

Language Identification (LID) systems are used to classify the spoken language from a given audio sample and are typically the first step for many spoken language processing tasks, such as Automatic Speech Recognition (ASR) systems. Without…

计算机视觉与模式识别 · 计算机科学 2017-08-17 Christian Bartz , Tom Herold , Haojin Yang , Christoph Meinel

This work focuses on the rapid development of linguistic annotation tools for resource-poor languages. We experiment several cross-lingual annotation projection methods using Recurrent Neural Networks (RNN) models. The distinctive feature…

计算与语言 · 计算机科学 2016-09-30 Othman Zennaki , Nasredine Semmar , Laurent Besacier

Adapting Automatic Speech Recognition (ASR) models to new domains results in a deterioration of performance on the original domain(s), a phenomenon called Catastrophic Forgetting (CF). Even monolingual ASR models cannot be extended to new…

音频与语音处理 · 电气工程与系统科学 2026-01-22 Steven Vander Eeckt , Hugo Van hamme

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…

计算与语言 · 计算机科学 2015-07-27 Haşim Sak , Andrew Senior , Kanishka Rao , Françoise Beaufays

The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very recently, as an alternative to LSTM layers, the Conformer…

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

计算与语言 · 计算机科学 2020-11-03 Chao-Wei Huang , Yun-Nung Chen

Recurrent neural networks (RNNs) are a widely used deep architecture for sequence modeling, generation, and prediction. Despite success in applications such as machine translation and voice recognition, these stateful models have several…

计算与语言 · 计算机科学 2020-04-23 Ankur Mali , Alexander Ororbia , Daniel Kifer , Clyde Lee Giles

Increasing the capacity of recurrent neural networks (RNN) usually involves augmenting the size of the hidden layer, with significant increase of computational cost. Recurrent neural tensor networks (RNTN) increase capacity using distinct…

计算与语言 · 计算机科学 2018-05-15 Alexandre Salle , Aline Villavicencio

We present two solutions to sentence-level SLR. Sentence-level SLR required mapping videos of sign language sentences to sequences of gloss labels. Connectionist Temporal Classification (CTC) has been used as the classifier level of both…

计算机视觉与模式识别 · 计算机科学 2022-11-29 Atra Akandeh

Language models, being at the heart of many NLP problems, are always of great interest to researchers. Neural language models come with the advantage of distributed representations and long range contexts. With its particular dynamics that…

神经与进化计算 · 计算机科学 2018-11-19 Thomas Cherian , Akshay Badola , Vineet Padmanabhan