Related papers: Addressing Cold Start Problem for End-to-end Autom…

Prompting method is regarded as one of the crucial progress for few-shot nature language processing. Recent research on prompting moves from discrete tokens based ``hard prompts'' to continuous ``soft prompts'', which employ learnable…

Code-Switching (CS) is a common linguistic phenomenon in multilingual communities that consists of switching between languages while speaking. This paper presents our investigations on end-to-end speech recognition for Mandarin-English CS…

KnowledgeTracing (KT) involves predicting students' knowledge states based on their interactions with Intelligent Tutoring Systems (ITS). A key challenge is the cold start problem, accurately predicting knowledge for new students with…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…

Modern end-to-end speech recognition models show astonishing results in transcribing audio signals into written text. However, conventional data feeding pipelines may be sub-optimal for low-resource speech recognition, which still remains a…

Language models such as Bidirectional Encoder Representations from Transformers (BERT) have been very effective in various Natural Language Processing (NLP) and text mining tasks including text classification. However, some tasks still pose…

The challenge of fairness arises when Automatic Speech Recognition (ASR) systems do not perform equally well for all sub-groups of the population. In the past few years there have been many improvements in overall speech recognition…

The item cold-start problem is crucial for online recommender systems, as the success of the cold-start phase determines whether items can transition into popular ones. Prompt learning, a powerful technique used in natural language…

We address the cold start problem in recommendation systems assuming no contextual information is available neither about users, nor items. We consider the case in which we only have access to a set of ratings of items by users. Most of the…

End-to-end (E2E) systems have shown comparable performance to hybrid systems for automatic speech recognition (ASR). Word timings, as a by-product of ASR, are essential in many applications, especially for subtitling and computer-aided…

Sequence-to-sequence (Seq2Seq) models with attention have excelled at tasks which involve generating natural language sentences such as machine translation, image captioning and speech recognition. Performance has further been improved by…

Prior research indicates that LID model performance significantly declines on accented speech; however, the specific causes, extent, and characterization of these errors remain under-explored. (i) We identify a common failure mode on…

The cold-start problem is quite challenging for existing recommendation models. Specifically, for the new items with only a few interactions, their ID embeddings are trained inadequately, leading to poor recommendation performance. Some…

We propose a new method of generating meaningful embeddings for speech, changes to four commonly used meta learning approaches to enable them to perform keyword spotting in continuous signals and an approach of combining their outcomes into…

Active learning promises to improve annotation efficiency by iteratively selecting the most important data to be annotated first. However, we uncover a striking contradiction to this promise: active learning fails to select data as…

This is the first work to investigate the effectiveness of BERT-based contextual embeddings in active learning (AL) tasks on cold-start scenarios, where traditional fine-tuning is infeasible due to the absence of labeled data. Our primary…

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…

End-to-end neural speaker diarization systems are able to address the speaker diarization task while effectively handling speech overlap. This work explores the incorporation of speaker information embeddings into the end-to-end systems to…

Speech to text models tend to be trained and evaluated against a single target accent. This is especially true for English for which native speakers from the United States became the main benchmark. In this work, we are going to show how…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…