相关论文: Back from the future: bidirectional CTC decoding u…

In automatic speech recognition, many studies have shown performance improvements using language models (LMs). Recent studies have tried to use bidirectional LMs (biLMs) instead of conventional unidirectional LMs (uniLMs) for rescoring the…

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…

The acoustic-to-word model based on the Connectionist Temporal Classification (CTC) criterion is a natural end-to-end (E2E) system directly targeting word as output unit. Two issues exist in the system: first, the current output of the CTC…

Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each time-step and the counterpart in the references as…

Audio tagging aims to assign predefined tags to audio clips to indicate the class information of audio events. Sequential audio tagging (SAT) means detecting both the class information of audio events, and the order in which they occur…

Attention-based models have made tremendous progress on end-to-end automatic speech recognition(ASR) recently. However, the conventional transformer-based approaches usually generate the sequence results token by token from left to right,…

Speech is one of the most effective ways of communication among humans. Even though audio is the most common way of transmitting speech, very important information can be found in other modalities, such as vision. Vision is particularly…

Predicting and executing a sequence of actions without intermediate replanning, known as action chunking, is increasingly used in robot learning from human demonstrations. Yet, its effects on the learned policy remain inconsistent: some…

Target speech extraction has attracted widespread attention. When microphone arrays are available, the additional spatial information can be helpful in extracting the target speech. We have recently proposed a channel decorrelation (CD)…

Diacritic restoration has gained importance with the growing need for machines to understand written texts. The task is typically modeled as a sequence labeling problem and currently Bidirectional Long Short Term Memory (BiLSTM) models…

Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence. However, it is not easy to get the best effect for bidirectional translation,…

This paper presents novel Weighted Finite-State Transducer (WFST) topologies to implement Connectionist Temporal Classification (CTC)-like algorithms for automatic speech recognition. Three new CTC variants are proposed: (1) the…

Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a \emph{temporal smoothing bias}: transient acoustic cues may be underutilized in favor of temporally smooth context that is…

Although frame-based models, such as CTC and transducers, have an affinity for streaming automatic speech recognition, their decoding uses no future knowledge, which could lead to incorrect pruning. Conversely, label-based attention…

Language models have recently been shown capable of performing regression wherein numeric predictions are represented as decoded strings. In this work, we provide theoretical grounds for this capability and furthermore investigate the…

We present Mask CTC, a novel non-autoregressive end-to-end automatic speech recognition (ASR) framework, which generates a sequence by refining outputs of the connectionist temporal classification (CTC). Neural sequence-to-sequence models…

We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and…

The two most common paradigms for end-to-end speech recognition are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models. It has been argued that the latter is better suited for learning an implicit…

Deep learning approaches have been widely used in Automatic Speech Recognition (ASR) and they have achieved a significant accuracy improvement. Especially, Convolutional Neural Networks (CNNs) have been revisited in ASR recently. However,…

We propose a novel method to accelerate training and inference process of recurrent neural network transducer (RNN-T) based on the guidance from a co-trained connectionist temporal classification (CTC) model. We made a key assumption that…