相关论文: Towards Real-time Mispronunciation Detection in Ki…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Current large language models (LLMs) often exhibit imbalanced multilingual capabilities due to their English-centric training corpora. To address this, existing fine-tuning approaches operating at the data-level (e.g., through data…

Selecting an appropriate response from many candidates given the utterances in a multi-turn dialogue is the key problem for a retrieval-based dialogue system. Existing work formalizes the task as matching between the utterances and a…

This paper introduces StutterNet, a novel deep learning based stuttering detection capable of detecting and identifying various types of disfluencies. Most of the existing work in this domain uses automatic speech recognition (ASR) combined…

Recent approaches for dialogue act recognition have shown that context from preceding utterances is important to classify the subsequent one. It was shown that the performance improves rapidly when the context is taken into account. We…

Recurrent neural networks (RNNs) have shown significant improvements in recent years for speech enhancement. However, the model complexity and inference time cost of RNNs are much higher than deep feed-forward neural networks (DNNs).…

In this work, our goals are two fold: large-vocabulary continuous sign language recognition (CSLR), and sign language retrieval. To this end, we introduce a multi-task Transformer model, CSLR2, that is able to ingest a signing sequence and…

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios. Differences in speaker accents are a significant source of such mismatch. The traditional approach to deal…

Scientific writing is difficult. It is even harder for those for whom English is a second language (ESL learners). Scholars around the world spend a significant amount of time and resources proofreading their work before submitting it for…

Speech models may be affected by performance imbalance in different population subgroups, raising concerns about fair treatment across these groups. Prior attempts to mitigate unfairness either focus on user-defined subgroups, potentially…

When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the…

Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…

In practical settings, a speaker recognition system needs to identify a speaker given a short utterance, while the enrollment utterance may be relatively long. However, existing speaker recognition models perform poorly with such short…

We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence…

Deep learning technology has been widely applied to speech enhancement. While testing the effectiveness of various network structures, researchers are also exploring the improvement of the loss function used in network training. Although…

Decoder-only large language models typically rely solely on masked causal attention, which limits their expressiveness by restricting information flow to one direction. We propose Bitune, a method that enhances pretrained decoder-only LLMs…

This work proposes a new learning target based on reverberation time shortening (RTS) for speech dereverberation. The learning target for dereverberation is usually set as the direct-path speech or optionally with some early reflections.…

Self-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing and disfluency detection in speech transcripts. Since the contextualized word…

The deployment of pre-trained perception models in novel environments often leads to performance degradation due to distributional shifts. Although recent artificial intelligence approaches for metacognition use logical rules to…