Related papers: Contextualized Streaming End-to-End Speech Recogni…

Phrases are essential to understand the core concepts in conversations. However, due to their rare occurrence in training data, correct translation of phrases is challenging in speech translation tasks. In this paper, we propose a phrase…

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…

Speech clarity and spatial audio immersion are the two most critical factors in enhancing remote conferencing experiences. Existing methods are often limited: either due to the lack of spatial information when using only one microphone, or…

Speech activity detection (SAD) plays an important role in current speech processing systems, including automatic speech recognition (ASR). SAD is particularly difficult in environments with acoustic noise. A practical solution is to…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Multilingual speech recognition has drawn significant attention as an effective way to compensate data scarcity for low-resource languages. End-to-end (e2e) modelling is preferred over conventional hybrid systems, mainly because of no…

End-to-End deep learning has shown promising results for speech enhancement tasks, such as noise suppression, dereverberation, and speech separation. However, most state-of-the-art methods for echo cancellation are either classical…

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

Machine learning algorithms such as linear regression, SVM and neural network have played an increasingly important role in the process of scientific discovery. However, none of them is both interpretable and accurate on nonlinear datasets.…

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of…

Automatic speech recognition (ASR) systems have achieved remarkable performance in common conditions but often struggle to leverage long-context information in contextualized scenarios that require domain-specific knowledge, such as…

At present, the deep end-to-end method based on supervised learning is used in entity recognition and dependency analysis. There are two problems in this method: firstly, background knowledge cannot be introduced; secondly, multi…

End-to-end learning framework is useful for building dialog systems for its simplicity in training and efficiency in model updating. However, current end-to-end approaches only consider user semantic inputs in learning and under-utilize…

End-to-end neural speaker diarization systems are able to address the speaker diarization task while effectively handling speech overlap. This work explores the incorporation of speaker information embeddings into the end-to-end systems to…

Sentiment analysis is attracting more and more attentions and has become a very hot research topic due to its potential applications in personalized recommendation, opinion mining, etc. Most of the existing methods are based on either…

Contextual automatic speech recognition (ASR) systems allow for recognizing out-of-vocabulary (OOV) words, such as named entities or rare words. However, it remains challenging due to limited training data and ambiguous or inconsistent…

Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage process: feature extraction and spatio-temporal context aggregation. In this paper, we propose an end-to-end ASD workflow where feature learning and…

We introduce a novel neural network module that adeptly handles recursive data flow in neural network architectures. At its core, this module employs a self-consistent approach where a set of recursive equations is solved iteratively,…

End-to-end (E2E) systems for automatic speech recognition (ASR), such as RNN Transducer (RNN-T) and Listen-Attend-Spell (LAS) blend the individual components of a traditional hybrid ASR system - acoustic model, language model, pronunciation…

Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data. While recently developed end-to-end methods largely simplify the modeling pipelines, they still suffer from the data…