Related papers: Less Is More: Improved RNN-T Decoding Using Limite…
A context-aware language model uses location, user and/or domain metadata (context) to adapt its predictions. In neural language models, context information is typically represented as an embedding and it is given to the RNN as an…
Sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing. Large-scale pre-trained language models…
This paper investigates the impact of word-based RNN language models (RNN-LMs) on the performance of end-to-end automatic speech recognition (ASR). In our prior work, we have proposed a multi-level LM, in which character-based and…
This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…
Adaption of end-to-end speech recognition systems to new tasks is known to be challenging. A number of solutions have been proposed which apply external language models with various fusion methods, possibly with a combination of two-pass…
Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…
The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…
Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
End-to-end (E2E) automatic speech recognition models like Recurrent Neural Networks Transducer (RNN-T) are becoming a popular choice for streaming ASR applications like voice assistants. While E2E models are very effective at learning…
In the last few years, Recurrent Neural Networks (RNNs) have proved effective on several NLP tasks. Despite such great success, their ability to model \emph{sequence labeling} is still limited. This lead research toward solutions where RNNs…
There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…
ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence. While optimizing the probability of all tokens in the target sequence is sensible, one may want to de-emphasize tokens…
In this paper, we explore the benefits of incorporating context into a Recurrent Neural Network (RNN-T) based Automatic Speech Recognition (ASR) model to improve the speech recognition for virtual assistants. Specifically, we use meta…
This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models. We redesign the standard nested-loop design for RNN-T decoding, swapping loops over frames and labels: the outer loop…
In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention Encoder-Decoder (AED), and RNN Transducer (RNN-T) are the…
This paper proposes a new approach to perform unsupervised fine-tuning and self-training using unlabeled speech data for recurrent neural network (RNN)-Transducer (RNN-T) end-to-end (E2E) automatic speech recognition (ASR) systems.…
Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…
When recurrent neural network transducers (RNNTs) are trained using the typical maximum likelihood criterion, the prediction network is trained only on ground truth label sequences. This leads to a mismatch during inference, known as…
Few-shot Named Entity Recognition (NER) aims to extract named entities using only a limited number of labeled examples. Existing contrastive learning methods often suffer from insufficient distinguishability in context vector representation…