Related papers: Speech Vecalign: an Embedding-based Method for Ali…
Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…
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…
The inherent synchronization between a speaker's lip movements, voice, and the underlying linguistic content offers a rich source of information for improving speech processing tasks, especially in challenging conditions where traditional…
Speech encodes multiple simultaneous attributes -- linguistic content, speaker identity, dialect, gender --that conventional single-vector embeddings conflate. We present a factor-partitioned embedding framework that maps each utterance…
While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set…
Current approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…
Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…
Large vision and language models show strong performance in tasks like image captioning, visual question answering, and retrieval. However, challenges remain in integrating speech, text, and vision into a unified model, especially for…
Tokenization serves as a foundational step for Large Language Models (LLMs) to process text. In new domains or languages, the inefficiency of the tokenizer will slow down the training and generation of LLM. The mismatch in vocabulary also…
A recent trend in speech processing is the use of embeddings created through machine learning models trained on a specific task with large datasets. By leveraging the knowledge already acquired, these models can be reused in new tasks where…
We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…
Existing Large Language Model (LLM) approaches to SystemVerilog Assertion (SVA) generation primarily focus on syntactic validity and formal verification outcomes, while semantic alignment between generated assertions and natural language…
Generalized end-to-end (GE2E) model is widely used in speaker verification (SV) fields due to its expandability and generality regardless of specific languages. However, the long-short term memory (LSTM) based on GE2E has two limitations:…
Text embedding models are designed for sentence-level applications like retrieval and semantic similarity, and are primarily evaluated on sentence-level benchmarks. Their behavior on isolated words is less understood. We show that simply…
Speech-to-Speech and Speech-to-Text translation are currently dynamic areas of research. In our commitment to advance these fields, we present SpeechAlign, a framework designed to evaluate the underexplored field of source-target alignment…
Traditional voice conversion methods rely on parallel recordings of multiple speakers pronouncing the same sentences. For real-world applications however, parallel data is rarely available. We propose MelGAN-VC, a voice conversion method…
The task of Visual Text-to-Speech (VisualTTS), also known as video dubbing, aims to generate speech synchronized with the lip movements in an input video, in additional to being consistent with the content of input text and cloning the…
PSDVec is a Python/Perl toolbox that learns word embeddings, i.e. the mapping of words in a natural language to continuous vectors which encode the semantic/syntactic regularities between the words. PSDVec implements a word embedding…