Related papers: CharManteau: Character Embedding Models For Portma…

This paper presents a novel approach to the acquisition of language models from corpora. The framework builds on Cobweb, an early system for constructing taxonomic hierarchies of probabilistic concepts that used a tabular, attribute-value…

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…

Previous text-to-image synthesis algorithms typically use explicit textual instructions to generate/manipulate images accurately, but they have difficulty adapting to guidance in the form of coarsely matched texts. In this work, we attempt…

We present Story2Board, a training-free framework for expressive storyboard generation from natural language. Existing methods narrowly focus on subject identity, overlooking key aspects of visual storytelling such as spatial composition,…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…

Textless spoken language models (SLMs) are generative models of speech that do not rely on text supervision. Most textless SLMs learn to predict the next semantic token, a discrete representation of linguistic content, and rely on a…

To accomplish punctuation restoration, most existing methods focus on introducing extra information (e.g., part-of-speech) or addressing the class imbalance problem. Recently, large-scale transformer-based pre-trained language models (PLMS)…

Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is important to capture the diversity in human speech such as speaker identities, prosodies, and styles (e.g., singing). Current large TTS systems usually…

Speech-to-text (S2T) summarization is a time-saving technique for filtering and keeping up with the broadcast news uploaded online on a daily basis. The rise of large language models from deep learning with impressive text generation…

The wayward quality of continuous prompts stresses the importance of their interpretability as unexpected and unpredictable behaviors appear following training, especially in the context of large language models automating people-sensitive…

Audio token modeling has become a powerful framework for speech synthesis, with two-stage approaches employing semantic tokens remaining prevalent. In this paper, we aim to simplify this process by introducing a semantic knowledge…

Direct speech-to-speech translation (S2ST) is an attractive research topic with many advantages compared to cascaded S2ST. However, direct S2ST suffers from the data scarcity problem because the corpora from speech of the source language to…

Speech-to-Speech Translation (S2ST) refers to the conversion of speech in one language into semantically equivalent speech in another language, facilitating communication between speakers of different languages. Speech-to-Discrete Unit…

Most recent approaches use the sequence-to-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words.…

Linguistic entrainment is a phenomenon where people tend to mimic each other in conversation. The core instrument to quantify entrainment is a linguistic similarity measure between conversational partners. Most of the current similarity…

In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at multiple granularities: neural lattice language models. These models construct a lattice of…

We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has a gate that adaptively finds the optimal mixture of the…

As one of the quintessence of Chinese traditional culture, couplet compromises two syntactically symmetric clauses equal in length, namely, an antecedent and subsequent clause. Moreover, corresponding characters and phrases at the same…

Language models (LMs) are pre-trained on raw text datasets to generate text sequences token-by-token. While this approach facilitates the learning of world knowledge and reasoning, it does not explicitly optimize for linguistic competence.…