Related papers: SANTLR: Speech Annotation Toolkit for Low Resource…

Speech emotion recognition systems often predict a consensus value generated from the ratings of multiple annotators. However, these models have limited ability to predict the annotation of any one person. Alternatively, models can learn to…

Data annotation and synthesis generally refers to the labeling or generating of raw data with relevant information, which could be used for improving the efficacy of machine learning models. The process, however, is labor-intensive and…

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Annotation projection is an important area in NLP that can greatly contribute to creating language resources for low-resource languages. Word alignment plays a key role in this setting. However, most of the existing word alignment methods…

Creating speech datasets, models, and evaluation frameworks for low-resource languages remains challenging given the lack of a broad base of pertinent experience to draw from. This paper reports on the field collection of 612 hours of…

Current dialogue summarization systems usually encode the text with a number of general semantic features (e.g., keywords and topics) to gain more powerful dialogue modeling capabilities. However, these features are obtained via open-domain…

Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promise is currently largely unrealized. We present a method that…

Annotation graphs and annotation servers offer infrastructure to support the analysis of human language resources in the form of time-series data such as text, audio and video. This paper outlines areas of common need among empirical…

The construction of high-quality parallel corpora for translation research has increasingly evolved from simple sentence alignment to complex, multi-layered annotation tasks. This methodological shift presents significant challenges for…

Phonetic representations are used when recording spoken languages, but no equivalent exists for recording signed languages. As a result, linguists have proposed several annotation systems that operate on the gloss or sub-unit level;…

In this work, our goals are two fold: large-vocabulary continuous sign language recognition (CSLR), and sign language retrieval. To this end, we introduce a multi-task Transformer model, CSLR2, that is able to ingest a signing sequence and…

We present a method for transferring pre-trained self-supervised (SSL) speech representations to multiple languages. There is an abundance of unannotated speech, so creating self-supervised representations from raw audio and fine-tuning on…

Non-verbal Vocalizations (NVs), such as laughter and sighs, are vital for conveying emotion and intention in human speech, yet most existing speech systems neglect them, which severely compromises communicative richness and emotional…

Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention. In this paper we describe the Semantic Entity Retrieval Toolkit (SERT) that provides implementations of our previously…

Low-resource languages face significant challenges due to the lack of sufficient linguistic data, resources, and tools for tasks such as supervised learning, annotation, and classification. This shortage hinders the development of accurate…

Speech synthesis (text to speech, TTS) and recognition (automatic speech recognition, ASR) are important speech tasks, and require a large amount of text and speech pairs for model training. However, there are more than 6,000 languages in…

This paper proposes a speech synthesis system that allows users to specify and control the acoustic characteristics of a speaker by means of prompts describing the speaker's traits of synthesized speech. Unlike previous approaches, our…

In this work, we create a web application to highlight the output of NLP models trained to parse and label discourse segments in law text. Our system is built primarily with journalists and legal interpreters in mind, and we focus on…

The development of resource-constrained approaches to automatic speech recognition (ASR) is of great interest due to its broad applicability to many low-resource languages for which there is scant usable data. Existing approaches to many…

We present a neural Sanskrit Natural Language Processing (NLP) toolkit named SanskritShala (a school of Sanskrit) to facilitate computational linguistic analyses for several tasks such as word segmentation, morphological tagging, dependency…