Related papers: Efficient conformer: Progressive downsampling and …
State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…
Attention layers are an integral part of modern end-to-end automatic speech recognition systems, for instance as part of the Transformer or Conformer architecture. Attention is typically multi-headed, where each head has an independent set…
Conformer has achieved impressive results in Automatic Speech Recognition (ASR) by leveraging transformer's capturing of content-based global interactions and convolutional neural network's exploiting of local features. In Conformer, two…
Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing…
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an…
Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target…
Recently, there has been an increasing interest in unifying streaming and non-streaming speech recognition models to reduce development, training and deployment cost. The best-known approaches rely on either window-based or dynamic…
In this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner. In particular, the audio and visual encoders learn to extract…
Conformer-based attention models have become the de facto backbone model for Automatic Speech Recognition tasks. A blank symbol is usually introduced to align the input and output sequences for CTC or RNN-T models. Unfortunately, the long…
Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…
Single-channel speech enhancement (SE) is an important task in speech processing. A widely used framework combines an analysis/synthesis filterbank with a mask prediction network, such as the Conv-TasNet architecture. In such systems, the…
Recently, attention-based encoder-decoder (AED) models have shown high performance for end-to-end automatic speech recognition (ASR) across several tasks. Addressing overconfidence in such models, in this paper we introduce the concept of…
The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…
Conformer has proven to be effective in many speech processing tasks. It combines the benefits of extracting local dependencies using convolutions and global dependencies using self-attention. Inspired by this, we propose a more flexible,…
Transformers provide a class of expressive architectures that are extremely effective for sequence modeling. However, the key limitation of transformers is their quadratic memory and time complexity $\mathcal{O}(L^2)$ with respect to the…
Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…
Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR).…
Conformers have recently been proposed as a promising modelling approach for automatic speech recognition (ASR), outperforming recurrent neural network-based approaches and transformers. Nevertheless, in general, the performance of these…
Connectionist Temporal Classification (CTC) is a widely used approach for automatic speech recognition (ASR) that performs conditionally independent monotonic alignment. However for translation, CTC exhibits clear limitations due to the…
The Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependencies. In this work we describe a faster, more…