相关论文: CTC-based Non-autoregressive Speech Translation

Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in real-time is…

Recently, contrastive learning attracts increasing interests in neural text generation as a new solution to alleviate the exposure bias problem. It introduces a sequence-level training signal which is crucial to generation tasks that always…

Autoregressive (AR) and Non-autoregressive (NAR) models are two types of generative models for Neural Machine Translation (NMT). AR models predict tokens in a word-by-word manner and can effectively capture the distribution of real…

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential…

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA (LayerNorm and…

This paper integrates a voice activity detection (VAD) function with end-to-end automatic speech recognition toward an online speech interface and transcribing very long audio recordings. We focus on connectionist temporal classification…

Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we…

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when…

Due to the unparallelizable nature of the autoregressive factorization, AutoRegressive Translation (ART) models have to generate tokens sequentially during decoding and thus suffer from high inference latency. Non-AutoRegressive Translation…

Automatic recognition systems for child speech are lagging behind those dedicated to adult speech in the race of performance. This phenomenon is due to the high acoustic and linguistic variability present in child speech caused by their…

Neural Transducer and connectionist temporal classification (CTC) are popular end-to-end automatic speech recognition systems. Due to their frame-synchronous design, blank symbols are introduced to address the length mismatch between…

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…

Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these two types of speech representations compare when used as…

Accent conversion aims to convert the accent of a source speech to a target accent, meanwhile preserving the speaker's identity. This paper introduces a novel non-autoregressive framework for accent conversion that learns accent-agnostic…

In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model. The bidirectional language model uses the future as well as the past…

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…

End-to-end speech translation (ST) is the task of translating speech signals in the source language into text in the target language. As a cross-modal task, end-to-end ST is difficult to train with limited data. Existing methods often try…

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…

Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance. However, existing NAT models are difficult to achieve the desired efficiency-quality…

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into…