相关论文: A Joint Model for Dropped Pronoun Recovery and Con…

As one of the major branches of automatic speech recognition, attention-based models greatly improves the feature representation ability of the model. In particular, the multi-head mechanism is employed in the attention, hoping to learn…

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units.…

Inspired by the theory of Leitners learning box from the field of psychology, we propose DropSample, a new method for training deep convolutional neural networks (DCNNs), and apply it to large-scale online handwritten Chinese character…

Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the…

Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven…

Speech enhancement algorithms based on deep learning have been improved in terms of speech intelligibility and perceptual quality greatly. Many methods focus on enhancing the amplitude spectrum while reconstructing speech using the mixture…

The topic of deep acoustic echo control (DAEC) has seen many approaches with various model topologies in recent years. Convolutional recurrent networks (CRNs), consisting of a convolutional encoder and decoder encompassing a recurrent…

Multi-speaker speech synthesis is a technique for modeling multiple speakers' voices with a single model. Although many approaches using deep neural networks (DNNs) have been proposed, DNNs are prone to overfitting when the amount of…

In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately. Most of the…

Paraphrasing exists at different granularity levels, such as lexical level, phrasal level and sentential level. This paper presents Decomposable Neural Paraphrase Generator (DNPG), a Transformer-based model that can learn and generate…

Deep prompt tuning (DPT) has gained great success in most natural language processing~(NLP) tasks. However, it is not well-investigated in dense retrieval where fine-tuning~(FT) still dominates. When deploying multiple retrieval tasks using…

Neural passage retrieval is a new and promising approach in open retrieval question answering. In this work, we stress-test the Dense Passage Retriever (DPR) -- a state-of-the-art (SOTA) open domain neural retrieval model -- on closed and…

Training dense passage representations via contrastive learning has been shown effective for Open-Domain Passage Retrieval (ODPR). Existing studies focus on further optimizing by improving negative sampling strategy or extra pretraining.…

Speech enhancement algorithms based on deep learning have greatly surpassed their traditional counterparts and are now being considered for the task of removing acoustic echo from hands-free communication systems. This is a challenging…

Methods for learning word representations using large text corpora have received much attention lately due to their impressive performance in numerous natural language processing (NLP) tasks such as, semantic similarity measurement, and…

Automatic dysarthric speech detection can provide reliable and cost-effective computer-aided tools to assist the clinical diagnosis and management of dysarthria. In this paper we propose a novel automatic dysarthric speech detection…

Image super-resolution pursuits reconstructing high-fidelity high-resolution counterpart for low-resolution image. In recent years, diffusion-based models have garnered significant attention due to their capabilities with rich prior…

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired…

When communicating with elders with cognitive impairment, cognitive stimulation (CS) help to maintain the cognitive health of elders. Data sparsity is the main challenge in building CS-based dialogue systems, particularly in the Chinese…

Speech dereverberation aims to alleviate the negative impact of late reverberant reflections. The weighted prediction error (WPE) method is a well-established technique known for its superior performance in dereverberation. However, in…