Related papers: Tuplemax Loss for Language Identification

Recent studies leverage large language models with multi-tasking capabilities, using natural language prompts to guide the model's behavior and surpassing performance of task-specific models. Motivated by this, we ask: can we build a single…

Building multispeaker neural network-based text-to-speech synthesis systems commonly relies on the availability of large amounts of high quality recordings from each speaker and conditioning the training process on the speaker's identity or…

Large language models (LLMs) are increasingly used as alternatives to traditional search engines given their capacity to generate text that resembles human language. However, this shift is concerning, as LLMs often generate hallucinations,…

In the recent past, a popular way of evaluating natural language understanding (NLU), was to consider a model's ability to perform natural language inference (NLI) tasks. In this paper, we investigate if NLI tasks, that are rarely used for…

Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to emit…

The advent of large language models (LLMs) has enabled significant performance gains in the field of natural language processing. However, recent studies have found that LLMs often resort to shortcuts when performing tasks, creating an…

The acoustic and linguistic features are important cues for the spoken language identification (LID) task. Recent advanced LID systems mainly use acoustic features that lack the usage of explicit linguistic feature encoding. In this paper,…

This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures…

This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. The former is defined as decomposing a potentially complex task into simpler subtasks while the latter consists in…

Despite advances in neural machine translation (NMT) quality, rare words continue to be problematic. For humans, the solution to the rare-word problem has long been dictionaries, but dictionaries cannot be straightforwardly incorporated…

The popular softmax loss and its recent extensions have achieved great success in the deep learning-based image classification. However, the data for training image classifiers usually has different quality. Ignoring such problem, the…

Pretrained multilingual large language models have typically used heuristic temperature-based sampling to balance between different languages. However previous work has not systematically evaluated the efficacy of different pretraining…

While most modern speech Language Identification methods are closed-set, we want to see if they can be modified and adapted for the open-set problem. When switching to the open-set problem, the solution gains the ability to reject an audio…

Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler…

Despite the recent ubiquity of large language models and their high zero-shot prompted performance across a wide range of tasks, it is still not known how well they perform on tasks which require processing of potentially idiomatic…

Deep networks have produced significant gains for various visual recognition problems, leading to high impact academic and commercial applications. Recent work in deep networks highlighted that it is easy to generate images that humans…

Multilingual speaker verification introduces the challenge of verifying a speaker in multiple languages. Existing systems were built using i-vector/x-vector approaches along with Bi-LSTMs, which were trained to discriminate speakers,…

Face recognition systems are widely deployed in high-security applications such as for biometric verification at border controls. Despite their high accuracy on pristine data, it is well-known that digital manipulations, such as face…

Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to…

We present a novel framework to exploit privileged information for recognition which is provided only during the training phase. Here, we focus on recognition task where images are provided as the main view and soft biometric traits…