相关论文: Dynamic Context-Aware Streaming Pretrained Languag…

Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases.…

Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of non-parallel data to guide transferring…

Recurrent Neural Networks (RNNs) have become the standard modeling technique for sequence data, and are used in a number of novel text-to-speech models. However, training a TTS model including RNN components has certain requirements for GPU…

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are…

We introduce a novel approach to incorporate syntax into natural language inference (NLI) models. Our method uses contextual token-level vector representations from a pretrained dependency parser. Like other contextual embedders, our method…

Streaming automatic speech recognition (ASR) models are restricted from accessing future context, which results in worse performance compared to the non-streaming models. To improve the performance of streaming ASR, knowledge distillation…

This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without use of any recurrent units. Recurrent neural networks (RNN) have become a standard technique to model sequential data…

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

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…

Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural…

The recent developments in technology have re-warded us with amazing audio synthesis models like TACOTRON and WAVENETS. On the other side, it poses greater threats such as speech clones and deep fakes, that may go undetected. To tackle…

In this paper we present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and…

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…

Multilingual text recognition (MLTR) systems typically focus on a fixed set of languages, which makes it difficult to handle newly added languages or adapt to ever-changing data distribution. In this paper, we propose the Incremental MLTR…

Dialog systems, such as voice assistants, are expected to engage with users in complex, evolving conversations. Unfortunately, traditional automatic speech recognition (ASR) systems deployed in such applications are usually trained to…

Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repeat words or produce…

Recent years have witnessed great progress in deep neural networks for real-time applications. However, most existing works do not explicitly consider the general case where the device's state and the available resources fluctuate over…

We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture…

Despite recent technology advancements, the effectiveness of neural approaches to end-to-end speech-to-text translation is still limited by the paucity of publicly available training corpora. We tackle this limitation with a method to…