Related papers: Improving coreference resolution with automaticall…

We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or…

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…

We propose a model to estimate the fundamental frequency in monophonic audio, often referred to as pitch estimation. We acknowledge the fact that obtaining ground truth annotations at the required temporal and frequency resolution is a…

Automatic dysarthric speech detection can provide reliable and cost-effective computer-aided tools to assist the clinical diagnosis and management of dysarthria. In this paper we propose a novel automatic dysarthric speech detection…

Accent normalization converts foreign-accented speech into native-like speech while preserving speaker identity. We propose a novel pipeline using self-supervised discrete tokens and non-parallel training data. The system extracts tokens…

Although speech and gesture recognition has been studied extensively, all the successful attempts of combining them in the unified framework were semantically motivated, e.g., keyword-gesture cooccurrence. Such formulations inherited the…

Text Proposals have emerged as a class-dependent version of object proposals - efficient approaches to reduce the search space of possible text object locations in an image. Combined with strong word classifiers, text proposals currently…

Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this…

For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech. Although inter-utterance linguistic information can influence the speech interpretation of the…

Semantic representations have long been argued as potentially useful for enforcing meaning preservation and improving generalization performance of machine translation methods. In this work, we are the first to incorporate information about…

The use of neural networks and deep learning techniques in image processing has significantly advanced the field, enabling highly accurate recognition results. However, achieving high recognition rates often necessitates complex network…

In automated pronunciation assessment, recent emphasis progressively lies on evaluating multiple aspects to provide enriched feedback. However, acquiring multi-aspect-score labeled data for non-native language learners' speech poses…

Training convolutional recurrent neural networks on first-order Ambisonics signals is a well-known approach when estimating the direction of arrival for speech/sound signals. In this work, we investigate whether increasing the order of…

Most recent coreference resolution systems use search algorithms over possible spans to identify mentions and resolve coreference. We instead present a coreference resolution system that uses a text-to-text (seq2seq) paradigm to predict…

This paper proposes an audio-conditioned phonemic and prosodic annotation model for building text-to-speech (TTS) datasets from unlabeled speech samples. For creating a TTS dataset that consists of label-speech paired data, the proposed…

We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by relying exclusively on synthetic data generated using a…

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilingual data. In this paper, we propose a novel data augmentation enhancement strategy for neural machine translation.…

Spontaneous speech presents several challenges for speech synthesis, particularly in capturing the natural flow of conversation, including turn-taking, pauses, and disfluencies. Although speech synthesis systems have made significant…

Emotions lie on a continuum, but current models treat emotions as a finite valued discrete variable. This representation does not capture the diversity in the expression of emotion. To better represent emotions we propose the use of natural…