Related papers: Guided contrastive self-supervised pre-training fo…
Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…
Despite recent advances in end-to-end speech recognition methods, their output is biased to the training data's vocabulary, resulting in inaccurate recognition of unknown terms or proper nouns. To improve the recognition accuracy for a…
Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and…
Goal-conditioned reinforcement learning has shown considerable potential in robotic manipulation; however, existing approaches remain limited by their reliance on prioritizing collected experience, resulting in suboptimal performance across…
This paper proposes an unsupervised data selection method by using a submodular function based on contrastive loss ratios of target and training data sets. A model using a contrastive loss function is trained on both sets. Then the ratio of…
Contrastive representation learning has been recently proved to be very efficient for self-supervised training. These methods have been successfully used to train encoders which perform comparably to supervised training on downstream…
Systems based on automatic speech recognition (ASR) technology can provide important functionality in computer assisted language learning applications. This is a young but growing area of research motivated by the large number of students…
The increasingly stringent requirement on quality-of-experience in 5G/B5G communication systems has led to the emerging neural speech enhancement techniques, which however have been developed in isolation from the existing expert-rule based…
Second pass rescoring is a critical component of competitive automatic speech recognition (ASR) systems. Large language models have demonstrated their ability in using pre-trained information for better rescoring of ASR hypothesis.…
Neural contextual biasing effectively improves automatic speech recognition (ASR) for crucial phrases within a speaker's context, particularly those that are infrequent in the training data. This work proposes contextual text injection…
Cycle consistent generative adversarial network (CycleGAN) and variational autoencoder (VAE) based models have gained popularity in non-parallel voice conversion recently. However, they often suffer from difficult training process and…
Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate…
Unexpected stimuli induce "error" or "surprise" signals in the brain. The theory of predictive coding promises to explain these observations in terms of Bayesian inference by suggesting that the cortex implements variational inference in a…
In step with the digitalization of transportation, we are witnessing a growing range of path-based smart-city applications, e.g., travel-time estimation and travel path ranking. A temporal path(TP) that includes temporal information, e.g.,…
In this paper, we propose the use of self-supervised pretraining on a large unlabelled data set to improve the performance of a personalized voice activity detection (VAD) model in adverse conditions. We pretrain a long short-term memory…
Deep biasing improves automatic speech recognition (ASR) performance by incorporating contextual phrases. However, most existing methods enhance subwords in a contextual phrase as independent units, potentially compromising contextual…
Existing contrastive learning methods for anomalous sound detection refine the audio representation of each audio sample by using the contrast between the samples' augmentations (e.g., with time or frequency masking). However, they might be…
We present a simple and efficient auxiliary loss function for automatic speech recognition (ASR) based on the connectionist temporal classification (CTC) objective. The proposed objective, an intermediate CTC loss, is attached to an…
Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In this paper, we…
Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity…