Related papers: Refining Targeted Syntactic Evaluation of Language…

The end-to-end TTS, which can predict speech directly from a given sequence of graphemes or phonemes, has shown improved performance over the conventional TTS. However, its predicting capability is still limited by the acoustic/phonetic…

Unsupervised sentence embedding aims to obtain the most appropriate embedding for a sentence to reflect its semantic. Contrastive learning has been attracting developing attention. For a sentence, current models utilize diverse data…

Target-dependent sentiment classification remains a challenge: modeling the semantic relatedness of a target with its context words in a sentence. Different context words have different influences on determining the sentiment polarity of a…

Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from…

While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic…

Sequence to sequence (seq2seq) models are often employed in settings where the target output is natural language. However, the syntactic properties of the language generated from these models are not well understood. We explore whether such…

With the advent of powerful neural language models over the last few years, research attention has increasingly focused on what aspects of language they represent that make them so successful. Several testing methodologies have been…

The thesis presents an attempt at using the syntactic structure in natural language for improved language models for speech recognition. The structured language model merges techniques in automatic parsing and language modeling using an…

Target speech extraction (TSE) extracts the speech of a target speaker in a mixture given auxiliary clues characterizing the speaker, such as an enrollment utterance. TSE addresses thus the challenging problem of simultaneously performing…

Although transformer-based Neural Language Models demonstrate impressive performance on a variety of tasks, their generalization abilities are not well understood. They have been shown to perform strongly on subject-verb number agreement in…

Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised…

As a practical alternative of speech separation, target speaker extraction (TSE) aims to extract the speech from the desired speaker using additional speaker cue extracted from the speaker. Its main challenge lies in how to properly extract…

This paper advances phrase break prediction (also known as phrasing) in multi-speaker text-to-speech (TTS) systems. We integrate speaker-specific features by leveraging speaker embeddings to enhance the performance of the phrasing model. We…

Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast array of these resources, most…

Text embedding models have significantly contributed to advancements in natural language processing by adeptly capturing semantic properties of textual data. However, the ability of these models to generalize across a wide range of…

Language-queried target sound extraction (TSE) aims to extract specific sounds from mixtures based on language queries. Traditional fully-supervised training schemes require extensively annotated parallel audio-text data, which are…

We present the first neural target speech extraction (TSE) system that uses human feedback for iterative refinement. Our approach allows users to mark specific segments of the TSE output, generating an edit mask. The refinement system then…

State-of-the-art target speaker extraction (TSE) systems are typically designed to generalize to any given mixing environment, necessitating a model with a large enough capacity as a generalist. Personalized speech enhancement could be a…

This work explores transfer learning from several synthetic languages to English. We investigate the structure of the embeddings in the fine-tuned models, the information they contain, and the capabilities of the fine-tuned models on simple…

Audio-Visual Target Speaker Extraction (AV-TSE) aims to mimic the human ability to enhance auditory perception using visual cues. Although numerous models have been proposed recently, most of them estimate target signals by primarily…