Related papers: Lattice-Free Sequence Discriminative Training for …

Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…

In label-noise learning, the transition matrix plays a key role in building statistically consistent classifiers. Existing consistent estimators for the transition matrix have been developed by exploiting anchor points. However, the…

Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art. In this paper we explore the efficiency of various pre-trained language models. We pre-train a list of…

Large language models (LLMs) have demonstrated remarkable capabilities in generating high-quality texts across diverse domains. However, the potential misuse of LLMs has raised significant concerns, underscoring the urgent need for reliable…

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Inferring the probability distribution of sentences or word sequences is a key process in natural language processing. While word-level language models (LMs) have been widely adopted for computing the joint probabilities of word sequences,…

Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

This work presents a novel objective function for the unsupervised training of neural network sentence encoders. It exploits signals from paragraph-level discourse coherence to train these models to understand text. Our objective is purely…

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…

Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…

We propose a novel class of language models, Latent Thought Models (LTMs), which incorporate explicit latent thought vectors that follow an explicit prior model in latent space. These latent thought vectors guide the autoregressive…

Speech recognition is a sequence prediction problem. Besides employing various deep learning approaches for framelevel classification, sequence-level discriminative training has been proved to be indispensable to achieve the…

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech…

Recent works on speech spoofing countermeasures still lack generalization ability to unseen spoofing attacks. This is one of the key issues of ASVspoof challenges especially with the rapid development of diverse and high-quality spoofing…

We describe a new framework for distilling information from word lattices to improve the accuracy of speech recognition and obtain a more perspicuous representation of a set of alternative hypotheses. In the standard MAP decoding approach…

User studies have shown that reducing the latency of our simultaneous lecture translation system should be the most important goal. We therefore have worked on several techniques for reducing the latency for both components, the automatic…

Target speaker extraction (TSE) aims to recover a target speaker's speech from a mixture using a reference utterance as a cue. Most TSE systems adopt conditional auto-encoder architectures with one-step inference. Inspired by test-time…

Recently, attempts have been made to remove Gaussian mixture models (GMM) from the training process of deep neural network-based hidden Markov models (HMM/DNN). For the GMM-free training of a HMM/DNN hybrid we have to solve two problems,…