相关论文: PairAlign: A Framework for Sequence Tokenization v…

A similarity join aims to find all similar pairs between two collections of records. Established approaches usually deal with synthetic differences like typos and abbreviations, but neglect the semantic relations between words. Such…

We address the text-to-text generation problem of sentence-level paraphrasing -- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies multiple-sequence alignment to sentences gathered…

Representation learning plays a central role in structuring internal embeddings to capture the statistical properties of language, influencing the coherence and contextual consistency of generated text. Statistical Coherence Alignment is…

Large Audio Language Models (LALMs) excel at semantic and paralinguistic tasks, yet their ability to perceive the fundamental physical attributes of audio such as pitch, loudness, and spatial location remains under-explored. To bridge this…

A key function of auditory cognition is the association of characteristic sounds with their corresponding semantics over time. Humans attempting to discriminate between fine-grained audio categories, often replay the same discriminative…

Multimodal large language models have fueled progress in image captioning. These models, fine-tuned on vast image datasets, exhibit a deep understanding of semantic concepts. In this work, we show that this ability can be re-purposed for…

This paper proposes a novel user-defined keyword spotting framework that accurately detects audio keywords based on text enrollment. Since audio data possesses additional acoustic information compared to text, there are discrepancies…

Using in-context learning (ICL) for data generation, techniques such as Self-Instruct (Wang et al., 2023) or the follow-up Alpaca (Taori et al., 2023) can train strong conversational agents with only a small amount of human supervision. One…

The intelligibility of speech relies on the ability of interlocutors to dynamically align their expectations about the rates at which informative changes in signals occur. Exactly how this is achieved remains an open question. We propose…

This paper describes an alignment-based model for interpreting natural language instructions in context. We approach instruction following as a search over plans, scoring sequences of actions conditioned on structured observations of text…

Discrete video VAEs underpin modern text-to-video generation and video understanding systems, yet existing tokenizers typically learn visual codebooks at a single scale with limited vocabularies and shallow language supervision, leading to…

Recent advances in audio-synchronized visual animation enable control of video content using audios from specific classes. However, existing methods rely heavily on expensive manual curation of high-quality, class-specific training videos,…

Movie dubbing aims to synthesize speech that preserves the vocal identity of a reference audio while synchronizing with the lip movements in a target video. Existing methods fail to achieve precise lip-sync and lack naturalness due to…

Audio-Language Models (ALMs), trained on paired audio-text data, are designed to process, understand, and reason about audio-centric multimodal content. Unlike traditional supervised approaches that use predefined labels, ALMs leverage…

In simultaneous interpreting, an interpreter renders a source speech into another language with a very short lag, much sooner than sentences are finished. In order to understand and later reproduce this dynamic and complex task…

We introduce conditional unigram tokenization, a novel approach that extends unigram tokenization by conditioning target token probabilities on source-language tokens from parallel data. Given a fixed source tokenizer, our method learns a…

This paper presents methods of making using of text supervision to improve the performance of sequence-to-sequence (seq2seq) voice conversion. Compared with conventional frame-to-frame voice conversion approaches, the seq2seq acoustic…

Tokenization is a crucial step in processing protein sequences for machine learning models, as proteins are complex sequences of amino acids that require meaningful segmentation to capture their functional and structural properties.…

Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for…

Speech language models (Speech LMs) enable end-to-end speech-text modeling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-text jointly decoding paradigm plays a critical role in…