中文
相关论文

相关论文: Multilingual Adaptation of RNN Based ASR Systems

200 篇论文

We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has a gate that adaptively finds the optimal mixture of the…

计算与语言 · 计算机科学 2016-10-14 Yasumasa Miyamoto , Kyunghyun Cho

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map…

机器学习 · 计算机科学 2021-10-27 Alexander Scheinker

Segmental conditional random fields (SCRFs) and connectionist temporal classification (CTC) are two sequence labeling methods used for end-to-end training of speech recognition models. Both models define a transcription probability by…

计算与语言 · 计算机科学 2017-06-07 Liang Lu , Lingpeng Kong , Chris Dyer , Noah A. Smith

Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are…

计算与语言 · 计算机科学 2018-03-08 Siddharth Dalmia , Ramon Sanabria , Florian Metze , Alan W. Black

Classification of sequence data is the topic of interest for dynamic Bayesian models and Recurrent Neural Networks (RNNs). While the former can explicitly model the temporal dependencies between class variables, the latter have a capability…

机器学习 · 计算机科学 2018-03-12 Son N. Tran , Srikanth Cherla , Artur Garcez , Tillman Weyde

Recurrent neural networks (RNNs) serve as a fundamental building block for many sequence tasks across natural language processing. Recent research has focused on recurrent dropout techniques or custom RNN cells in order to improve…

计算与语言 · 计算机科学 2017-08-04 Stephen Merity , Bryan McCann , Richard Socher

Vision-and-Language Navigation (VLN) is a realistic but challenging task that requires an agent to locate the target region using verbal and visual cues. While significant advancements have been achieved recently, there are still two broad…

计算机视觉与模式识别 · 计算机科学 2024-04-17 Liuyi Wang , Zongtao He , Jiagui Tang , Ronghao Dang , Naijia Wang , Chengju Liu , Qijun Chen

Research on multilingual speech recognition remains attractive yet challenging. Recent studies focus on learning shared structures under the multi-task paradigm, in particular a feature sharing structure. This approach has been found…

计算与语言 · 计算机科学 2016-09-28 Zhiyuan Tang , Lantian Li , Dong Wang

In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstraction gap between input acoustic signals and output linguistic…

音频与语音处理 · 电气工程与系统科学 2022-02-09 Yosuke Higuchi , Keita Karube , Tetsuji Ogawa , Tetsunori Kobayashi

Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…

音频与语音处理 · 电气工程与系统科学 2022-10-31 Alejandro Gomez-Alanis , Lukas Drude , Andreas Schwarz , Rupak Vignesh Swaminathan , Simon Wiesler

Conversational speech, while being unstructured at an utterance level, typically has a macro topic which provides larger context spanning multiple utterances. The current language models in speech recognition systems using recurrent neural…

音频与语音处理 · 电气工程与系统科学 2020-08-11 Srikanth Raj Chetupalli , Sriram Ganapathy

It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take…

神经与进化计算 · 计算机科学 2015-07-08 Aram Ter-Sarkisov , Holger Schwenk , Loic Barrault , Fethi Bougares

We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR) model. We learn to listen and write characters with a joint Connectionist Temporal Classification (CTC) and attention-based encoder-decoder network. The encoder is…

计算与语言 · 计算机科学 2017-06-12 Takaaki Hori , Shinji Watanabe , Yu Zhang , William Chan

Here we present a novel approach to conditioning the SampleRNN generative model for voice conversion (VC). Conventional methods for VC modify the perceived speaker identity by converting between source and target acoustic features. Our…

声音 · 计算机科学 2018-10-30 Cong Zhou , Michael Horgan , Vivek Kumar , Cristina Vasco , Dan Darcy

Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To…

计算与语言 · 计算机科学 2020-04-10 Shaojie Jiang , Thomas Wolf , Christof Monz , Maarten de Rijke

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

计算与语言 · 计算机科学 2024-12-24 Keqi Deng , Jinxi Guo , Yingyi Ma , Niko Moritz , Philip C. Woodland , Ozlem Kalinli , Mike Seltzer

Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on…

计算与语言 · 计算机科学 2024-09-25 Devang Kulshreshtha , Saket Dingliwal , Brady Houston , Nikolaos Pappas , Srikanth Ronanki

Neural approaches to sequence labeling often use a Conditional Random Field (CRF) to model their output dependencies, while Recurrent Neural Networks (RNN) are used for the same purpose in other tasks. We set out to establish RNNs as an…

机器学习 · 计算机科学 2018-10-02 Saeed Najafi , Colin Cherry , Grzegorz Kondrak

Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference.…

计算与语言 · 计算机科学 2017-10-31 Bin Wang , Zhijian Ou

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of…

计算与语言 · 计算机科学 2019-06-17 Markus Kitza , Pavel Golik , Ralf Schlüter , Hermann Ney