Related papers: Non-native children speech recognition through tra…

Classroom environments are particularly challenging for children with hearing impairments, where background noise, multiple talkers, and reverberation degrade speech perception. These difficulties are greater for children than adults, yet…

The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation…

In this paper, we describe the details of the neural dependency parser sub-mitted by our team to the NLPCC 2019 Shared Task of Semi-supervised do-main adaptation subtask on Cross-domain Dependency Parsing. Our system is based on the…

Emotion recognition from speech is one of the key steps towards emotional intelligence in advanced human-machine interaction. Identifying emotions in human speech requires learning features that are robust and discriminative across diverse…

Automatic dubbing, which generates a corresponding version of the input speech in another language, could be widely utilized in many real-world scenarios such as video and game localization. In addition to synthesizing the translated…

Despite the remarkable progress achieved on automatic speech recognition, recognizing far-field speeches mixed with various noise sources is still a challenging task. In this paper, we introduce novel student-teacher transfer learning,…

In this paper we exploit cross-lingual models to enable dialogue act recognition for specific tasks with a small number of annotations. We design a transfer learning approach for dialogue act recognition and validate it on two different…

Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advances, ASR models like Whisper struggle with non-normative…

Building named entity recognition (NER) models for languages that do not have much training data is a challenging task. While recent work has shown promising results on cross-lingual transfer from high-resource languages to low-resource…

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

Domain adaptation is critical for learning in new and unseen environments. With domain adversarial training, deep networks can learn disentangled and transferable features that effectively diminish the dataset shift between the source and…

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

The field of speech processing has undergone a transformative shift with the advent of deep learning. The use of multiple processing layers has enabled the creation of models capable of extracting intricate features from speech data. This…

Deep neural networks excel at learning from labeled data and achieve state-of-the-art resultson a wide array of Natural Language Processing tasks. In contrast, learning from unlabeled data, especially under domain shift, remains a…

English pretrained language models, which make up the backbone of many modern NLP systems, require huge amounts of unlabeled training data. These models are generally presented as being trained only on English text but have been found to…

In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers. Inspired by the recent success of deep neural networks (DNNs) in semantic inferencing, triplet…

Speech-to-speech translation is a typical sequence-to-sequence learning task that naturally has two directions. How to effectively leverage bidirectional supervision signals to produce high-fidelity audio for both directions? Existing…

In this paper, we present a study of the recent advancements which have helped bring Transfer Learning to NLP through the use of semi-supervised training. We discuss cutting-edge methods and architectures such as BERT, GPT, ELMo, ULMFit…

A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effective transfer learning approach that addresses the problem of…