Related papers: Context-Dependent Acoustic Modeling without Explic…

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…

This paper reports our work on building up a Cantonese Speech-to-Text (STT) system with a syllable based acoustic model. This is a part of an effort in building a STT system to aid dyslexic students who have cognitive deficiency in writing…

The performance of speaker diarization is strongly affected by its clustering algorithm at the test stage. However, it is known that clustering algorithms are sensitive to random noises and small variations, particularly when the clustering…

State-of-the-art semantic image segmentation methods are mostly based on training deep convolutional neural networks (CNNs). In this work, we proffer to improve semantic segmentation with the use of contextual information. In particular, we…

Language models (LMs) based on Long Short Term Memory (LSTM) have shown good gains in many automatic speech recognition tasks. In this paper, we extend an LSTM by adding highway networks inside an LSTM and use the resulting Highway LSTM…

Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and…

Speech foundation models have recently demonstrated the ability to perform Speech In-Context Learning (SICL). Selecting effective in-context examples is crucial for SICL performance, yet selection methodologies remain underexplored. In this…

Frequency modulation features capture the fine structure of speech formants that constitute beneficial and supplementary to the traditional energy-based cepstral features. Improvements have been demonstrated mainly in GMM-HMM systems for…

This paper presents our latest investigations on dialog act (DA) classification on automatically generated transcriptions. We propose a novel approach that combines convolutional neural networks (CNNs) and conditional random fields (CRFs)…

Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context information into a…

While models in audio and speech processing are becoming deeper and more end-to-end, they as a consequence need expensive training on large data, and are often brittle. We build on a classical model of human hearing and make it…

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…

This work tackles the problem of learning a set of language specific acoustic units from unlabeled speech recordings given a set of labeled recordings from other languages. Our approach may be described by the following two steps procedure:…

In order to successfully perform tasks specified by natural language instructions, an artificial agent operating in a visual world needs to map words, concepts, and actions from the instruction to visual elements in its environment. This…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

Deep neural networks (DNNs) have been successfully applied to a wide variety of acoustic modeling tasks in recent years. These include the applications of DNNs either in a discriminative feature extraction or in a hybrid acoustic modeling…

This study borrows and extends probabilistic language models from natural language processing to discover the syntactic properties of tonal harmony. Language models come in many shapes and sizes, but their central purpose is always the…

Automatic speech recognition (ASR) is a relevant area in multiple settings because it provides a natural communication mechanism between applications and users. ASRs often fail in environments that use language specific to particular…

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-language tasks is challenging due to differences in acoustic…

How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks are usually a great choice and a promising way. However,…